© 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. 2749
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    import statement followed by module name

    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
    ].
    -0.08
    ush
    -0.07
    .con
    -0.07
    ).
    -0.05
    ren
    -0.02
    ag
    -0.02
    lif
    -0.02
    ¿
    -0.02
    ud
    -0.01
    du
    -0.01
    POSITIVE LOGITS
    ing
    0.10
    ce
    0.07
    ces
    0.07
    ers
    0.07
    ings
    0.07
    cies
    0.06
    ed
    0.06
    er
    0.05
    es
    0.05
    anage
    0.05
    Activations Density 17.198%

    No Known Activations