© 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. 3356
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    async 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
    ail
    -0.05
    !
    -0.05
    cond
    -0.04
    ctionary
    -0.04
    dividual
    -0.04
    ark
    -0.04
    .co
    -0.04
    def
    -0.03
    dices
    -0.03
    maining
    -0.03
    POSITIVE LOGITS
     {↵
    0.08
     {'
    0.08
     {"
    0.08
    ati
    0.07
    c
    0.06
     v
    0.05
    d
    0.04
    ru
    0.04
    v
    0.04
    n
    0.04
    Activations Density 0.076%

    No Known Activations