© 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. 2645
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    opening parenthesis or keyword

    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
    ±
    -0.06
    [row
    -0.04
    _grid
    -0.04
    >
    -0.03
    07
    -0.03
    bab
    -0.03
    quence
    -0.02
    quen
    -0.02
    gment
    -0.02
    None
    -0.02
    POSITIVE LOGITS
    m
    0.06
    me
    0.05
    mo
    0.05
    M
    0.05
    mm
    0.05
    em
    0.04
    mory
    0.04
    ls
    0.04
    mit
    0.04
    Ĺ
    0.04
    Activations Density 12.619%

    No Known Activations