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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 2245
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    self.attribute or method access (negative activations)

    python-code · gemini-2.5-flash-lite

    method definitions using self

    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
    "]
    -0.03
     _
    -0.02
    ']
    -0.02
    _count
    -0.01
    mport
    -0.01
     count
    -0.01
     function
    -0.01
    .con
    -0.01
    dule
    -0.01
    import
    -0.01
    POSITIVE LOGITS
    ],
    0.04
    '],
    0.03
    ).
    0.03
    ,↵
    0.03
    .split
    0.02
    &
    0.02
    (),
    0.02
    split
    0.02
    .read
    0.02
    .strip
    0.02
    Activations Density 89.826%

    No Known Activations