© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 1977
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    set union method

    python-code · gemini-2.5-flash-lite

    class definition or variable declaration (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
     represe
    -0.04
     representing
    -0.04
     between
    -0.04
     represent
    -0.04
    adjac
    -0.03
     two
    -0.03
    uccess
    -0.03
    wo
    -0.03
     conne
    -0.03
    duct
    -0.03
    POSITIVE LOGITS
    py
    0.06
    dule
    0.05
    uil
    0.04
     sys
    0.03
     code
    0.03
     run
    0.03
    inal
    0.03
    gorithm
    0.03
    result
    0.03
    ases
    0.03
    Activations Density 58.612%

    No Known Activations