© 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. 3285
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string literals inside print statements (negative activations)

    python-code · gemini-2.5-flash-lite

    method calls and keywords like `def`

    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
    m
    -0.06
    mit
    -0.05
    _with
    -0.04
    etween
    -0.04
     Calculate
    -0.04
    ge
    -0.04
    _for
    -0.04
     us
    -0.03
    .s
    -0.03
     between
    -0.03
    POSITIVE LOGITS
    or
    0.05
     dp
    0.04
    isited
    0.03
     or
    0.03
    and
    0.03
    _comb
    0.03
    sible
    0.03
    o
    0.03
    _counts
    0.02
    ari
    0.02
    Activations Density 80.283%

    No Known Activations