© 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. 2551
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `def` keyword or `import` statement

    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
    olver
    -0.05
    tices
    -0.04
     model
    -0.04
    times
    -0.04
    odel
    -0.04
    anage
    -0.03
    ties
    -0.03
    erate
    -0.02
    ..
    -0.02
    ty
    -0.02
    POSITIVE LOGITS
     Di
    0.06
    di
    0.06
    yp
    0.05
    (di
    0.05
    _di
    0.04
     di
    0.04
     sum
    0.04
    _sum
    0.04
    itial
    0.04
     <=
    0.03
    Activations Density 66.711%

    No Known Activations