{"total":20,"rows":[{"id":"2503.24071","title":"From Colors to Classes: Emergence of Concepts in Vision Transformers","created":"2025-03-31","cited_by_count":23,"area":null},{"id":"2311.16681","title":"Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations","created":"2023-11-28","cited_by_count":22,"area":null},{"id":"2405.06855","title":"Linear Explanations for Individual Neurons","created":"2024-05-10","cited_by_count":19,"area":null},{"id":"2405.20331","title":"CoSy: Evaluating Textual Explanations of Neurons","created":"2024-05-30","cited_by_count":17,"area":null},{"id":"2506.15538","title":"Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework","created":"2025-06-18","cited_by_count":10,"area":null},{"id":"2408.17198","title":"Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features","created":"2024-08-30","cited_by_count":7,"area":null},{"id":"2406.08572","title":"LLM-assisted Concept Discovery: Automatically Identifying and Explaining Neuron Functions","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2502.13606","title":"LaVCa: LLM-assisted Visual Cortex Captioning","created":"2025-02-19","cited_by_count":4,"area":null},{"id":"2401.06122","title":"Manipulating Feature Visualizations with Gradient Slingshots","created":"2024-01-11","cited_by_count":3,"area":null},{"id":"2502.16105","title":"NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions","created":"2025-02-22","cited_by_count":3,"area":null},{"id":"2411.10019","title":"Towards Utilising a Range of Neural Activations for Comprehending Representational Associations","created":"2024-11-15","cited_by_count":2,"area":null},{"id":"2501.05205","title":"Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning","created":"2025-01-09","cited_by_count":2,"area":null},{"id":"2501.13818","title":"Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2405.10552","title":"Data Science Principles for Interpretable and Explainable AI","created":"2024-05-17","cited_by_count":1,"area":null},{"id":"2407.06286","title":"Characterization of topological structures in different neural network architectures","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2511.18359","title":"TRANSPORTER: Transferring Visual Semantics from VLM Manifolds","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2511.20931","title":"Open Vocabulary Compositional Explanations for Neuron Alignment","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2511.20934","title":"Guaranteed Optimal Compositional Explanations for Neurons","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2604.08039","title":"LINE: LLM-based Iterative Neuron Explanations for Vision Models","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.22477","title":"Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples","created":"2026-04-24","cited_by_count":0,"area":null}],"next_cursor":null}