© 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. 2-MLP
    11. 3590
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    exponent operator (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
     se
    -0.04
    _se
    -0.04
    [n
    -0.04
    osition
    -0.03
    os
    -0.03
    (n
    -0.03
     n
    -0.03
    (w
    -0.03
     pos
    -0.03
    .n
    -0.02
    POSITIVE LOGITS
    sition
    0.10
    rence
    0.09
    dint
    0.09
    sions
    0.08
    ighbor
    0.08
    timal
    0.08
    didate
    0.08
    tices
    0.08
    tex
    0.08
    section
    0.08
    Activations Density 99.060%

    No Known Activations