© 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. 2278
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    exponentiation to 0.5 or 0.5 exponent

    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
    ig
    -0.06
    e
    -0.06
    .index
    -0.05
    ir
    -0.04
    es
    -0.04
    v
    -0.03
    le
    -0.03
     as
    -0.03
    ed
    -0.03
    uel
    -0.02
    POSITIVE LOGITS
    .e
    0.10
    ase
    0.07
    sp
    0.07
    ame
    0.06
    .c
    0.06
    ameters
    0.06
    ate
    0.05
    ates
    0.04
     j
    0.04
     import
    0.03
    Activations Density 14.462%

    No Known Activations