© 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. 2-MLP
    11. 5786
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    async and assert statements

    python-code · gemini-2.5-flash-lite

    the 'for' keyword (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
     enumerate
    -0.12
    ack
    -0.07
    dint
    -0.06
    end
    -0.06
    reshold
    -0.06
    95
    -0.05
    rib
    -0.05
    ange
    -0.05
    get
    -0.04
    _mo
    -0.04
    POSITIVE LOGITS
    gth
    0.08
    .w
    0.07
    (w
    0.07
    his
    0.07
     representing
    0.07
    ize
    0.06
    xtend
    0.06
    s
    0.06
    lot
    0.06
    ilities
    0.06
    Activations Density 100.000%

    No Known Activations