© 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. 2-MLP
    11. 7919
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    exponentiation or keyword argument unpacking

    python-code · gemini-2.5-flash-lite

    conditional statement start (negative activations)

    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
    .ran
    -0.09
     route
    -0.07
    .randint
    -0.07
    _shortest
    -0.07
    _route
    -0.07
    (route
    -0.07
    _city
    -0.06
    route
    -0.06
     routes
    -0.06
    _routes
    -0.06
    POSITIVE LOGITS
    ies
    0.08
    ied
    0.08
    ments
    0.07
    y
    0.07
     continue
    0.07
    ment
    0.07
    Y
    0.06
    yp
    0.06
    hildren
    0.06
    endencies
    0.06
    Activations Density 100.000%

    No Known Activations