# WWW: A Unified Framework for Explaining What, Where and Why of Neural Networks by Interpretation of Neuron Concepts

arXiv: https://arxiv.org/abs/2402.18956 · HTML: https://mlsanity.com/paper/2402.18956/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 29 references that are in the map.
- First posted on arXiv 29 Feb 2024.

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [A Survey on Neural Network Interpretability](https://mlsanity.com/paper/2012.14261/) (2020)
- [CRAFT: Concept Recursive Activation FacTorization for Explainability](https://mlsanity.com/paper/2211.10154/) (2022)
- [Compositional Explanations of Neurons](https://mlsanity.com/paper/2006.14032/) (2020)
- [Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI](https://mlsanity.com/paper/2010.07487/) (2020)
- [CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks](https://mlsanity.com/paper/2204.10965/) (2022)
- [From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation](https://mlsanity.com/paper/2206.03208/) (2022)
- [Natural Language Descriptions of Deep Visual Features](https://mlsanity.com/paper/2201.11114/) (2022)
- [Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks](https://mlsanity.com/paper/1801.03454/) (2018)
- [A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation](https://mlsanity.com/paper/2306.07304/) (2023)
- [LINe: Out-of-Distribution Detection by Leveraging Important Neurons](https://mlsanity.com/paper/2303.13995/) (2023)
- [Neural Response Interpretation through the Lens of Critical Pathways](https://mlsanity.com/paper/2103.16886/) (2021)
- [Identifying Interpretable Subspaces in Image Representations](https://mlsanity.com/paper/2307.10504/) (2023)
- [Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information](https://mlsanity.com/paper/2110.01471/) (2021)
- [HINT: Hierarchical Neuron Concept Explainer](https://mlsanity.com/paper/2203.14196/) (2022)

## Built on by (most cited first, 14 of 14)

- [Mechanistic understanding and validation of large AI models with SemanticLens](https://mlsanity.com/paper/2501.05398/) (2025)
- [From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance](https://mlsanity.com/paper/2505.20229/) (2025)
- [Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition](https://mlsanity.com/paper/2511.03725/) (2025)
- [PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition](https://mlsanity.com/paper/2504.13140/) (2025)
- [CE-FAM: Concept-Based Explanation via Fusion of Activation Maps](https://mlsanity.com/paper/2509.23849/) (2025)
- [What is Missing? Explaining Neurons Activated by Absent Concepts](https://mlsanity.com/paper/2603.09787/) (2026)
- [When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities](https://mlsanity.com/paper/2607.08605/) (2026)
- [Mask-Free Neuron Concept Annotation for Interpreting Neural Networks in Medical Domain](https://mlsanity.com/paper/2407.11375/) (2024)
- [Toward Neurosymbolic Program Comprehension](https://mlsanity.com/paper/2502.01806/) (2025)
- [Caption-Driven Explainability: Probing CNNs for Bias via CLIP](https://mlsanity.com/paper/2510.22035/) (2025)
- [Guaranteed Optimal Compositional Explanations for Neurons](https://mlsanity.com/paper/2511.20934/) (2025)
- [UNBOX: Unveiling Black-box visual models with Natural-language](https://mlsanity.com/paper/2603.08639/) (2026)
- [Select, Hypothesize and Verify: Towards Verified Neuron Concept Interpretation](https://mlsanity.com/paper/2603.24953/) (2026)
- [Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples](https://mlsanity.com/paper/2604.22477/) (2026)

## Abstract (arXiv)

Recent advancements in neural networks have showcased their remarkable capabilities across various domains. Despite these successes, the "black box" problem still remains. Addressing this, we propose a novel framework, WWW, that offers the 'what', 'where', and 'why' of the neural network decisions in human-understandable terms. Specifically, WWW utilizes adaptive selection for concept discovery, employing adaptive cosine similarity and thresholding techniques to effectively explain 'what'. To address the 'where' and 'why', we proposed a novel combination of neuron activation maps (NAMs) with Shapley values, generating localized concept maps and heatmaps for individual inputs. Furthermore, WWW introduces a method for predicting uncertainty, leveraging heatmap similarities to estimate 'how' reliable the prediction is. Experimental evaluations of WWW demonstrate superior performance in both quantitative and qualitative metrics, outperforming existing methods in interpretability. WWW provides a unified solution for explaining 'what', 'where', and 'why', introducing a method for localized explanations from global interpretations and offering a plug-and-play solution adaptable to various architectures.