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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 6025
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    parentheses, comma, and operator (negative activations)

    python-code · gemini-2.5-flash-lite

    index of zero in a list

    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
     def
    -0.03
    [int
    -0.03
    [t
    -0.03
    [str
    -0.03
    [s
    -0.02
    [start
    -0.02
     with
    -0.02
    [
    -0.02
    -0.01
    -0.01
    POSITIVE LOGITS
     P
    0.00
    from
    0.00
     results
    0.00
    import
    0.00
     pass
    0.00
     raise
    0.00
     break
    0.00
    _dict
    0.00
    Error
    0.00
    __
    0.00
    Activations Density 99.946%

    No Known Activations