© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5585
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    accessing class attributes (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment with equals sign

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    import
    -0.04
     import
    -0.03
    from
    -0.02
     +=
    -0.02
     from
    -0.02
     sum
    -0.01
     to
    -0.01
    ameters
    -0.01
    ness
    -0.01
    am
    -0.01
    POSITIVE LOGITS
     Testing
    0.02
     Test
    0.02
    print
    0.02
    _with
    0.01
    ith
    0.01
     whe
    0.01
    sert
    0.01
     typing
    0.01
     with
    0.01
     that
    0.01
    Activations Density 83.525%

    No Known Activations