© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 7037
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    import statements (negative activations)

    python-code · gemini-2.5-flash-lite

    print statement with keyword arguments

    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
     found
    -0.05
    (len
    -0.05
    .index
    -0.04
     ver
    -0.04
    .set
    -0.03
     while
    -0.03
     dfs
    -0.03
    ackage
    -0.03
     from
    -0.02
    _value
    -0.02
    POSITIVE LOGITS
    udoku
    0.08
    .values
    0.07
    _population
    0.07
    opulation
    0.06
    aze
    0.06
     graph
    0.05
    .items
    0.05
     grid
    0.05
    otal
    0.04
     abs
    0.04
    Activations Density 99.989%

    No Known Activations