© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 4463
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    beginning of a function call or tuple

    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
     name
    -0.05
     This
    -0.04
    ames
    -0.04
    .name
    -0.04
    igh
    -0.04
    _name
    -0.04
    (
    -0.04
    le
    -0.03
    |
    -0.03
    name
    -0.03
    POSITIVE LOGITS
    N
    0.08
    sw
    0.07
    re
    0.06
    count
    0.06
    per
    0.06
    w
    0.05
     N
    0.05
     run
    0.05
    city
    0.05
    he
    0.05
    Activations Density 19.961%

    No Known Activations