© 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. 7102
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    range followed by parentheses (negative activations)

    python-code · gemini-2.5-flash-lite

    attribute assignment

    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
    isited
    -0.04
     between
    -0.04
    .s
    -0.03
    mmon
    -0.03
     two
    -0.03
     input
    -0.03
     rows
    -0.03
    wo
    -0.02
    _to
    -0.02
     other
    -0.02
    POSITIVE LOGITS
     If
    0.02
    .append
    0.02
     -=
    0.02
    Ö
    0.02
    .remove
    0.02
     St
    0.02
     Testing
    0.02
    .add
    0.02
     +=
    0.02
     G
    0.01
    Activations Density 59.961%

    No Known Activations