© 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. 3589
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `urllib.request` or `urllib.parse` imports

    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
     {↵
    -0.03
    (N
    -0.03
    inf
    -0.03
    qrt
    -0.02
    ith
    -0.02
    ak
    -0.02
     are
    -0.02
    (map
    -0.02
     with
    -0.02
     product
    -0.02
    POSITIVE LOGITS
     spe
    0.06
     given
    0.06
    ory
    0.06
    hest
    0.06
    zero
    0.05
    rent
    0.05
    ren
    0.04
    b
    0.04
    resh
    0.04
    ments
    0.04
    Activations Density 38.971%

    No Known Activations