# Explanatory models in neuroscience: Part 1 -- taking mechanistic abstraction seriously

arXiv: https://arxiv.org/abs/2104.01490 · HTML: https://mlsanity.com/paper/2104.01490/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2021.

## Built on by (most cited first, 18 of 18)

- [Language models show human-like content effects on reasoning tasks](https://mlsanity.com/paper/2207.07051/) (2022)
- [The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units](https://mlsanity.com/paper/2411.02280/) (2024)
- [Neural Foundations of Mental Simulation: Future Prediction of Latent Representations on Dynamic Scenes](https://mlsanity.com/paper/2305.11772/) (2023)
- [Evaluating Multiview Object Consistency in Humans and Image Models](https://mlsanity.com/paper/2409.05862/) (2024)
- [A Rubric for Human-like Agents and NeuroAI](https://mlsanity.com/paper/2212.04401/) (2022)
- [From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks](https://mlsanity.com/paper/2405.15164/) (2024)
- [A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i](https://mlsanity.com/paper/2505.00808/) (2025)
- [Model Alignment Search](https://mlsanity.com/paper/2501.06164/) (2025)
- [Model-brain comparison using inter-animal transforms](https://mlsanity.com/paper/2510.02523/) (2025)
- [A newborn embodied Turing test for view-invariant object recognition](https://mlsanity.com/paper/2306.05582/) (2023)
- [Multiple Realizability and the Rise of Deep Learning](https://mlsanity.com/paper/2405.13231/) (2024)
- [Human-level 3D shape perception emerges from multi-view learning](https://mlsanity.com/paper/2602.17650/) (2026)
- [Zero-shot World Models Are Developmentally Efficient Learners](https://mlsanity.com/paper/2604.10333/) (2026)
- [Lil-Bevo: Explorations of Strategies for Training Language Models in More Humanlike Ways](https://mlsanity.com/paper/2310.17591/) (2023)
- [Characterizing higher-order representations through generative diffusion models explains human decoded neurofeedback performance](https://mlsanity.com/paper/2503.14333/) (2025)
- [Sparse components distinguish visual pathways & their alignment to neural networks](https://mlsanity.com/paper/2510.08858/) (2025)
- [Bears, all bears, and some bears. Language Constraints on Language Models' Inductive Inferences](https://mlsanity.com/paper/2601.09852/) (2026)
- [Large Language Models as Modal Models in Linguistics](https://mlsanity.com/paper/2606.10467/) (2026)

## Abstract (arXiv)

Despite the recent success of neural network models in mimicking animal performance on visual perceptual tasks, critics worry that these models fail to illuminate brain function. We take it that a central approach to explanation in systems neuroscience is that of mechanistic modeling, where understanding the system is taken to require fleshing out the parts, organization, and activities of a system, and how those give rise to behaviors of interest. However, it remains somewhat controversial what it means for a model to describe a mechanism, and whether neural network models qualify as explanatory. We argue that certain kinds of neural network models are actually good examples of mechanistic models, when the right notion of mechanistic mapping is deployed. Building on existing work on model-to-mechanism mapping (3M), we describe criteria delineating such a notion, which we call 3M++. These criteria require us, first, to identify a level of description that is both abstract but detailed enough to be "runnable", and then, to construct model-to-brain mappings using the same principles as those employed for brain-to-brain mapping across individuals. Perhaps surprisingly, the abstractions required are those already in use in experimental neuroscience, and are of the kind deployed in the construction of more familiar computational models, just as the principles of inter-brain mappings are very much in the spirit of those already employed in the collection and analysis of data across animals. In a companion paper, we address the relationship between optimization and intelligibility, in the context of functional evolutionary explanations. Taken together, mechanistic interpretations of computational models and the dependencies between form and function illuminated by optimization processes can help us to understand why brain systems are built they way they are.