{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T12:39:38Z","timestamp":1764333578036,"version":"3.45.0"},"reference-count":73,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T00:00:00Z","timestamp":1759795200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T00:00:00Z","timestamp":1759795200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001866","name":"Fonds National de la Recherche Luxembourg","doi-asserted-by":"publisher","award":["C22\/SC\/17111440\/EAI"],"award-info":[{"award-number":["C22\/SC\/17111440\/EAI"]}],"id":[{"id":"10.13039\/501100001866","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Minds & Machines"],"DOI":"10.1007\/s11023-025-09745-w","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T12:27:30Z","timestamp":1759840050000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Clarifying the Opacity of Neural Networks"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5056-0039","authenticated-orcid":false,"given":"Thomas","family":"Raleigh","sequence":"first","affiliation":[]},{"given":"Aleks","family":"Knoks","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,7]]},"reference":[{"key":"9745_CR1","doi-asserted-by":"publisher","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","volume":"6","author":"A Adadi","year":"2018","unstructured":"Adadi, A., & Berrada, M. (2018). Peeking inside the black-box: A survey on explainable artificial intelligence (XAI). IEEE Access, 6, 52138\u201352160.","journal-title":"IEEE Access"},{"key":"9745_CR2","first-page":"857","volume":"108","author":"B Babic","year":"2023","unstructured":"Babic, B., & Cohen, I. (2023). The algorithmic explainability \u201cBait and Switch.\u201d Minnesota Law Review, 108, 857\u2013909.","journal-title":"Minnesota Law Review"},{"key":"9745_CR3","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1126\/science.abg1834","volume":"373","author":"B Babic","year":"2021","unstructured":"Babic, B., Gerke, S., Evgeniou, T., & Cohen, I. (2021). Beware explanations from AI in healthcare. Science, 373, 284\u2013286.","journal-title":"Science"},{"issue":"7","key":"9745_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0130140","volume":"10","author":"S Bach","year":"2015","unstructured":"Bach, S., Binder, A., Montavon, G., Klauschen, F., M\u00fcller, K.-R., & Samek, W. (2015). On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE, 10(7), 1\u201346.","journal-title":"PLoS ONE"},{"key":"9745_CR5","unstructured":"Bereska, L., & Gavves, E. (2024). Mechanistic interpretability for AI safety: A review. Retrieved September 3, 2024, from https:\/\/arxiv.org\/html\/2404.14082v2"},{"issue":"1","key":"9745_CR6","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/s11023-021-09569-4","volume":"32","author":"F Boge","year":"2021","unstructured":"Boge, F. (2021). Two dimensions of opacity and the deep learning predicament. Minds and Machines, 32(1), 43\u201375.","journal-title":"Minds and Machines"},{"issue":"26","key":"9745_CR7","first-page":"1","volume":"35","author":"F Boge","year":"2025","unstructured":"Boge, F., & Mosig, A. (2025). Put it to the test: Getting serious about explanation in Explainable Artificial Intelligence. Minds and Machines, 35(26), 1\u201328.","journal-title":"Minds and Machines"},{"key":"9745_CR8","unstructured":"Bricken, T., Templeton, A., Baston, J., Chen, B., Jermyn, A., Conerly, T., Turner, N., Anil, C., Denison, C., Askell, A., Lasenby, R., Wu, Y., Kravec, S., Schiefer, N., Maxwell, T., Joseph, N., Tamkin, A., Nguyen, K., McLean, B., Burke, J., Hume, T., Carter, S., Henighan, T., & Olah C. (2023). Towards monosemanticity: Decomposing language models with dictionary learning. Transformer Circuits Thread. Retrieved September 3, 2024, from https:\/\/transformer-circuits.pub\/2023\/monosemantic-features\/index.html"},{"issue":"2","key":"9745_CR9","first-page":"1","volume":"24","author":"J Browning","year":"2022","unstructured":"Browning, J., & Theunissen, M. (2022). Putting explainable AI in context: Institutional explanations for medical AI. Ethics and Information Technology, 24(2), 1\u201310.","journal-title":"Ethics and Information Technology"},{"issue":"1","key":"9745_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/2053951715622512","volume":"3","author":"J Burrell","year":"2016","unstructured":"Burrell, J. (2016). How the machine \u201cthinks\u201d: Understanding opacity in machine learning algorithms. Big Data & Society, 3(1), 1\u201312.","journal-title":"Big Data & Society"},{"issue":"2","key":"9745_CR11","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s11229-022-03522-3","volume":"200","author":"R Cao","year":"2022","unstructured":"Cao, R. (2022). Putting representations to use. Synthese, 200(2), 151.","journal-title":"Synthese"},{"key":"9745_CR12","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780192894724.001.0001","volume-title":"Making AI intelligible: Philosophical foundations","author":"H Capellen","year":"2021","unstructured":"Capellen, H., & Dever, J. (2021). Making AI intelligible: Philosophical foundations. Oxford University Press."},{"issue":"3","key":"9745_CR13","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1080\/09515089308573094","volume":"6","author":"D Chalmers","year":"1993","unstructured":"Chalmers, D. (1993). Connectionism and compositionality: Why Fodor and Pylyshyn were wrong. Philosophical Psychology, 6(3), 305\u2013319.","journal-title":"Philosophical Psychology"},{"issue":"4","key":"9745_CR14","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1086\/709729","volume":"87","author":"K Creel","year":"2020","unstructured":"Creel, K. (2020). Transparency in complex computational systems. Philosophy of Science, 87(4), 568\u2013589.","journal-title":"Philosophy of Science"},{"issue":"4","key":"9745_CR15","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/BF02551274","volume":"2","author":"G Cybenko","year":"1989","unstructured":"Cybenko, G. (1989). Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems, 2(4), 303\u2013314.","journal-title":"Mathematics of Control, Signals, and Systems"},{"key":"9745_CR16","unstructured":"Davies, X., Nadeau, M., Prakash, N., Rott Shahan, T., & Bau, D. (2023), Discovering variable binding circuitry with desiderata. In Proceeding of the ICML 2023 Workshop Challenges of Deploying Generative AI."},{"key":"9745_CR17","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1038\/s41586-023-06622-3","volume":"622","author":"J Durairaj","year":"2023","unstructured":"Durairaj, J., Waterhouse, A., Mets, T., Brodiazhenko, T., Abdullah, M., Studer, G., Tauriello, G., Akdel, M., Andreeva, A., Bateman, A., Tenson, T., Hauryliuk, V., Schwede, T., & Pereira, J. (2023). Uncovering new families and folds in the natural protein universe. Nature, 622, 646\u2013653.","journal-title":"Nature"},{"key":"9745_CR18","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1136\/medethics-2021-107531","volume":"47","author":"J Dur\u00e1n","year":"2021","unstructured":"Dur\u00e1n, J., & Jongsma, K. (2021). Who is afraid of black box algorithms? On the epistemological and ethical basis of trust in medical AI. Journal of Medical Ethics, 47, 329\u2013335.","journal-title":"Journal of Medical Ethics"},{"key":"9745_CR19","unstructured":"Elhage, N., Hume, T., Olsson, C., Schiefer, N., Henighan, T., Kravec, S., Hatfield-Dodds, Z., Lasenby, R., Drain, D., Chen, C., Grosse, R., McCandish, S., Kaplan, J., Amodei, D., Wattenberg, M., & Olah, C. (2022). Toy models of superposition. Transformer Circuits Thread. Retrieved September 3, 2024, from https:\/\/arxiv.org\/pdf\/2209.10652"},{"key":"9745_CR20","doi-asserted-by":"publisher","first-page":"1165622","DOI":"10.3389\/fpsyg.2023.1165622","volume":"14","author":"L Favela","year":"2023","unstructured":"Favela, L., & Machery, E. (2023). Investigating the concept of representation in the neural and psychological sciences. Frontiers in Psychology, 14, 1165622. https:\/\/doi.org\/10.3389\/fpsyg.2023.1165622","journal-title":"Frontiers in Psychology"},{"issue":"4","key":"9745_CR21","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1017\/epi.2022.39","volume":"19","author":"W Fleischer","year":"2022","unstructured":"Fleischer, W. (2022). Understanding, idealization, and explainable AI. Episteme, 19(4), 534\u2013560.","journal-title":"Episteme"},{"issue":"1\u20132","key":"9745_CR22","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/0010-0277(88)90031-5","volume":"28","author":"J Fodor","year":"1988","unstructured":"Fodor, J., & Pylyshyn, Z. (1988). Connectionism and cognitive architecture: A critical analysis. Cognition, 28(1\u20132), 3\u201371.","journal-title":"Cognition"},{"key":"9745_CR23","doi-asserted-by":"crossref","unstructured":"Fong, R., & Vedaldi, A. (2017). Interpretable explanations of black boxes by meaningful perturbation. In Proceedings of the 2017 IEEE International Conference on Computer Vision (pp. 1\u20139).","DOI":"10.1109\/ICCV.2017.371"},{"issue":"6","key":"9745_CR24","first-page":"513","volume":"117","author":"O Gingerich","year":"1973","unstructured":"Gingerich, O. (1973). From copernicus to kepler: Heliocentrism as model and as reality. Proceedings of the American Philosophical Society, 117(6), 513\u2013522.","journal-title":"Proceedings of the American Philosophical Society"},{"issue":"2","key":"9745_CR25","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/s11229-024-04723-8","volume":"204","author":"J Grindrod","year":"2024","unstructured":"Grindrod, J. (2024). Large Language Models and linguistic intentionality. Synthese, 204(2), 71.","journal-title":"Synthese"},{"key":"9745_CR26","doi-asserted-by":"crossref","unstructured":"Grzankowski, A. (2024). Real sparks of artificial intelligence and the importance of inner interpretability. Inquiry 1\u201327.","DOI":"10.1080\/0020174X.2023.2296468"},{"issue":"5","key":"9745_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3236009","volume":"51","author":"R Guidotti","year":"2018","unstructured":"Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2018). A survey of methods for explaining black box models. Acm Computing Surveys, 51(5), 1\u201342.","journal-title":"Acm Computing Surveys"},{"key":"9745_CR28","unstructured":"Hanin, B., & Selke, M. (2018). Approximating continuous functions by ReLU Nets of minimal width. Retrieved September 3, 2024, from https:\/\/arxiv.org\/pdf\/1710.11278"},{"key":"9745_CR29","unstructured":"Hanna, M., Liu, O., & Variengein, A. (2023). How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model. In NeurIPS Conference. Retrieved September 3, 2024, from https:\/\/openreview.net\/pdf?id=p4PckNQR8k"},{"issue":"1","key":"9745_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18564\/jasss.1873","volume":"15","author":"E Hatna","year":"2012","unstructured":"Hatna, E., & Benenson, I. (2012). The schelling model of ethnic residential dynamics: Beyond the integrated-segregated dichotomy of patterns. Journal of Artificial Societies and Social Simulation, 15(1), 1\u20136.","journal-title":"Journal of Artificial Societies and Social Simulation"},{"key":"9745_CR31","unstructured":"Heimersheim, S., & Jett, J. (2023). A circuit for Python docstrings in a 4-layer attention-only transformer. Retrieved August 15, 2024, from https:\/\/www.lesswrong.com\/posts\/u6KXXmKFbXfWzoAXn\/a-circuit-for-python-docstrings-in-a-4-layer-attention-only"},{"key":"9745_CR32","unstructured":"Hernandez, E., Sen Sharma, A., Haklay, T., Meng, K., Wattenberg, M., Andreas, J., Belinkov, Y., & Bau, D. (2023) Linearity of relation decoding in transformer language models. In Proceeding of the 13th International Conference on Learning Representations (ICLR 2024). Retrieved September 3, 2024, from https:\/\/openreview.net\/pdf?id=w7LU2s14kE"},{"key":"9745_CR33","first-page":"359","volume-title":"Neural networks","author":"K Hornik","year":"1989","unstructured":"Hornik, K., Stitchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural networks (Vol. 2, pp. 359\u2013366). Pergamon Press."},{"key":"9745_CR34","unstructured":"Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., & Veigas, F. (2018), Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). Proceedings of the 35th International Conference on Machine Learning (PMLR18) (pp. 2668\u20132677)."},{"key":"9745_CR35","volume-title":"The structure of scientific revolutions","author":"T Kuhn","year":"1962","unstructured":"Kuhn, T. (1962). The structure of scientific revolutions. University of Chicago Press."},{"key":"9745_CR36","unstructured":"Li, K., Hopkins, A., Bau, D., Vi\u00e9gas, Pfister, H., & Wattenberg, M. (2023). Emergent world representations: Exploring a sequence model trained on a synthetic task. In Proceedings of the 11th International Conference on Learning Representations (ICLR 2023). Retrieved September 3, 2024, from https:\/\/openreview.net\/pdf?id=DeG07_TcZvT"},{"key":"9745_CR37","unstructured":"Lindsey, J., Gurnee, W., Ameisen, E., Chen, B., Pearce, A., Turner, N. L., Citro, C., Abrahams, D., Carter, S., Hosmer, B., & Marcus, J. (2025) On the biology of a large language model. Transformer Circuits."},{"key":"9745_CR38","unstructured":"Lundberg, S. M., & Lee, S, (2017). A unified approach to interpreting model predictions. In NeurIPS (4765\u20134774)."},{"issue":"1","key":"9745_CR39","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1023\/A:1023336924671","volume":"18","author":"P Mandik","year":"2003","unstructured":"Mandik, P. (2003). Varieties of representation in evolved and embodied neural networks. Biology and Philosophy, 18(1), 95\u2013130.","journal-title":"Biology and Philosophy"},{"key":"9745_CR40","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/0004-3702(77)90013-3","volume":"9","author":"D Marr","year":"1977","unstructured":"Marr, D. (1977). Artificial intelligence: A personal view. Artificial Intelligence, 9, 37\u201348.","journal-title":"Artificial Intelligence"},{"key":"9745_CR41","volume-title":"Vision: A computational investigation into the human representation and processing of visual information","author":"D Marr","year":"1982","unstructured":"Marr, D. (1982). Vision: A computational investigation into the human representation and processing of visual information. W. H. Freeman and Company."},{"key":"9745_CR42","unstructured":"Molnar, C. (2021), Interpretable Machine Learning: A Guide for Making Black Box Models Explainable. Retrieved September 3, 2024, from https:\/\/originalstatic.aminer.cn\/misc\/pdf\/Molnar-interpretable-machine-learning_compressed.pdf"},{"key":"9745_CR43","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/j.patcog.2016.11.008","volume":"65","author":"G Montavon","year":"2017","unstructured":"Montavon, G., Bach, S., Binder, A., Samek, W., & M\u00fcller, K.-R. (2017). Explaining nonlinear classification decisions with deep taylor decomposition. Pattern Recognition, 65, 211\u2013222.","journal-title":"Pattern Recognition"},{"issue":"1","key":"9745_CR44","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/s10670-019-00185-4","volume":"87","author":"B Nanay","year":"2019","unstructured":"Nanay, B. (2019). Entity realism about mental representations. Erkenntnis, 87(1), 75\u201391.","journal-title":"Erkenntnis"},{"key":"9745_CR45","unstructured":"Nanda, N., Chan, L., Lieberum, T., & Steinhardt, J. (2023), Progress measures for grokking via mechanistic interpretability. In Proceedings of the 11th International Conference on Learning Representations (ICLR 2023). Retrieved September 3, 2024, from https:\/\/openreview.net\/forum?id=9XFSbDPmdW"},{"key":"9745_CR46","doi-asserted-by":"crossref","unstructured":"Olah, C., Cammarata, N., Schubert, L., Goh. G., Petrov, M. & Carter. S. (2020). Zoom in: An introduction to circuits. Distill. Retrieved August 15, 2024, from https:\/\/distill.pub\/2020\/circuits\/zoom-in","DOI":"10.23915\/distill.00024.001"},{"key":"9745_CR47","doi-asserted-by":"crossref","unstructured":"O\u2019Mahoney, L., Andrearczyk, V., Muller H., & Graziani, M. (2023), Disentangling neuron representations with concept vectors. In Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 3770\u20133775).","DOI":"10.1109\/CVPRW59228.2023.00390"},{"key":"9745_CR48","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1007\/s11023-019-09502-w","volume":"29","author":"A P\u00e1ez","year":"2019","unstructured":"P\u00e1ez, A. (2019). The pragmatic turn in explainable artificial intelligence (XAI). Minds and Machines, 29, 441\u2013459.","journal-title":"Minds and Machines"},{"key":"9745_CR49","unstructured":"Quirke, P., & Barez, F. (2024), Understanding addition in transformers. Proceedings of the 12th International Conference on Learning Representations (ICLR 2024). Retrieved September 3, 2024, from https:\/\/arxiv.org\/pdf\/2310.13121"},{"key":"9745_CR50","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1007\/s43681-022-00141-z","volume":"2","author":"E Ratti","year":"2022","unstructured":"Ratti, E., & Graves, M. (2022). Explainable machine learning practices: Opening another black box for reliable medical AI. AI and Ethics, 2, 801\u2013814.","journal-title":"AI and Ethics"},{"issue":"5","key":"9745_CR51","doi-asserted-by":"publisher","first-page":"1823","DOI":"10.1007\/s10670-022-00605-y","volume":"89","author":"T R\u00e4z","year":"2024","unstructured":"R\u00e4z, T., & Beisbart, C. (2024). The importance of understanding deep learning. Erkenntnis, 89(5), 1823\u20131840.","journal-title":"Erkenntnis"},{"key":"9745_CR52","doi-asserted-by":"crossref","unstructured":"Ribeiro, M., Singh, S., & Guestrin, C. (2016). Why should I trust you? Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD \u201916) (pp. 1135\u20131144). ACM Press.","DOI":"10.1145\/2939672.2939778"},{"key":"9745_CR53","doi-asserted-by":"crossref","unstructured":"Ribeiro, M., Singh, S., & Guestrin, C. (2018). Anchors: High-precision model-agnostic explanations. In Proceedings of the 32nd AAAI conference on artificial intelligence and 30th Innovative Applications of Artificial Intelligence Conference and 8th AAAI Symposium on Educational Advances in Artificial Intelligence (pp. 1527\u20131535). ACM Press.","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"9745_CR54","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2011\/07\/P07006","author":"T Rogers","year":"2011","unstructured":"Rogers, T., & McKane, A. (2011). A unified framework for Schelling\u2019s model of segregation. Journal of Statistical Mechanics: Theory and Experiment. https:\/\/doi.org\/10.1088\/1742-5468\/2011\/07\/P07006","journal-title":"Journal of Statistical Mechanics: Theory and Experiment"},{"issue":"173","key":"9745_CR55","first-page":"1","volume":"203","author":"D Rowbottom","year":"2024","unstructured":"Rowbottom, D., Peden, W., & Curtis-Trudel, A. (2024). Does the no miracles argument apply to AI? Synthese, 203(173), 1\u201320.","journal-title":"Synthese"},{"key":"9745_CR56","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1038\/s42256-019-0048-x","volume":"1","author":"C Rudin","year":"2019","unstructured":"Rudin, C. (2019). Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Nature Machine Intelligence, 1, 206\u2013215.","journal-title":"Nature Machine Intelligence"},{"issue":"3","key":"9745_CR57","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1017\/S0140525X00005756","volume":"3","author":"J Searle","year":"1980","unstructured":"Searle, J. (1980). Minds, brains and programs. Behavioral and Brain Sciences, 3(3), 417\u2013457.","journal-title":"Behavioral and Brain Sciences"},{"issue":"2","key":"9745_CR58","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1080\/0022250X.1971.9989794","volume":"1","author":"T Schelling","year":"1971","unstructured":"Schelling, T. (1971). Dynamic models of segregation. The Journal of Mathematical Sociology, 1(2), 143\u2013186.","journal-title":"The Journal of Mathematical Sociology"},{"key":"9745_CR59","unstructured":"Sharkey, L. (2024). Sparsify: A mechanistic interpretability research agenda. AI Alignment Forum. Retrieved August 15, 2024, from https:\/\/www.alignmentforum.org\/posts\/64MizJXzyvrYpeKqm\/sparsify-a-mechanistic-interpretability-research-agenda."},{"key":"9745_CR60","volume-title":"Meaning in mind: Fodor and his critics","author":"P Smolensky","year":"1991","unstructured":"Smolensky, P. (1991). Connectionism, constituency, and the language of thought. In B. M. Loewer & G. Rey (Eds.), Meaning in mind: Fodor and his critics. Blackwell."},{"issue":"3","key":"9745_CR61","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1017\/can.2024.1","volume":"53","author":"A S\u00f8gaard","year":"2023","unstructured":"S\u00f8gaard, A. (2023). On the opacity of deep neural networks. Canadian Journal of Philosophy, 53(3), 224\u2013239.","journal-title":"Canadian Journal of Philosophy"},{"key":"9745_CR62","doi-asserted-by":"crossref","unstructured":"Speith, T. (2022). A review of taxonomies of explainable artificial intelligence (XAI) methods. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency (FAC 2022) (pp. 2239\u20132250).","DOI":"10.1145\/3531146.3534639"},{"issue":"1","key":"9745_CR63","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1093\/bjps\/axz035","volume":"73","author":"E Sullivan","year":"2022","unstructured":"Sullivan, E. (2022a). Understanding from machine learning models. The British Journal for the Philosophy of Science, 73(1), 109\u2013133.","journal-title":"The British Journal for the Philosophy of Science"},{"issue":"5","key":"9745_CR64","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1017\/psa.2022.62","volume":"89","author":"E Sullivan","year":"2022","unstructured":"Sullivan, E. (2022b). Inductive risk, understanding, and opaque machine learning models. Philosophy of Science, 89(5), 1065\u20131074.","journal-title":"Philosophy of Science"},{"key":"9745_CR65","doi-asserted-by":"crossref","unstructured":"Tan, J., & Zhang, Y. (2023). ExplainableFold: Understanding AlphaFold prediction with explainable AI. In Proceedings of the 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD \u201923). ACM Press.","DOI":"10.1145\/3580305.3599337"},{"issue":"1","key":"9745_CR66","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/s11023-018-9459-4","volume":"28","author":"E Thomson","year":"2018","unstructured":"Thomson, E., & Piccinini, G. (2018). Neural representations observed. Minds and Machines, 28(1), 191\u2013235.","journal-title":"Minds and Machines"},{"key":"9745_CR67","unstructured":"Tigges, C., Hollingsworth, O., Geiger, A., & Nanda, N. (2023). Linear representations of sentiment in Large Language Models. Retrieved September 3, 2024, from https:\/\/arxiv.org\/pdf\/2310.15154"},{"key":"9745_CR68","doi-asserted-by":"publisher","first-page":"101174","DOI":"10.1016\/j.cogsys.2023.101174","volume":"83","author":"L Titus","year":"2024","unstructured":"Titus, L. (2024). \u2018Does ChatGPT have semantic understanding?\u2019 Cognitive Systems Research, 83, 101174.","journal-title":"Cognitive Systems Research"},{"key":"9745_CR69","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aan6080","author":"S Wachter","year":"2017","unstructured":"Wachter, S., Mittelstadt, B., & Floridi, L. (2017). Transparent, explainable, and accountable AI for robotics. Science Robotics. https:\/\/doi.org\/10.1126\/scirobotics.aan6080","journal-title":"Science Robotics"},{"key":"9745_CR70","unstructured":"Wang, K., Variengien, A., Conmy, A., Shlegeris, B., & Steinhardt, J. (2023). Interpretability in the wild: A circuit for indirect object identification in GPT-2 small. In Proceedings of the 11th International Conference on Learning Representations (ICLR 2023). Retrieved September 3, 2024, from https:\/\/arxiv.org\/pdf\/2211.00593"},{"issue":"2","key":"9745_CR71","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/s13347-019-00382-7","volume":"34","author":"C Zednik","year":"2019","unstructured":"Zednik, C. (2019). Solving the black box problem: A normative framework for explainable artificial intelligence. Philosophy & Technology, 34(2), 265\u2013288.","journal-title":"Philosophy & Technology"},{"issue":"1","key":"9745_CR72","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/psa.2021.13","volume":"89","author":"J Zerilli","year":"2022","unstructured":"Zerilli, J. (2022). Explaining machine learning decisions. Philosophy of Science, 89(1), 1\u201319.","journal-title":"Philosophy of Science"},{"key":"9745_CR73","unstructured":"Zintgraf, L., Cohen, T., Adel, T., & Welling, M. (2017). Visualizing deep neural network decisions: Prediction difference analysis. In Proceedings of the 5th International Conference on Learning Representations (ICLR 2017). Retrieved September 3, 2024, from https:\/\/openreview.net\/pdf?id=BJ5UeU9xx"}],"container-title":["Minds and Machines"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11023-025-09745-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11023-025-09745-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11023-025-09745-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T06:04:53Z","timestamp":1763705093000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11023-025-09745-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,7]]},"references-count":73,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["9745"],"URL":"https:\/\/doi.org\/10.1007\/s11023-025-09745-w","relation":{},"ISSN":["1572-8641"],"issn-type":[{"type":"electronic","value":"1572-8641"}],"subject":[],"published":{"date-parts":[[2025,10,7]]},"assertion":[{"value":"1 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declares that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"43"}}