© 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. 1954
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing parenthesis or brace

    python-code · gemini-2.5-flash-lite

    function call arguments (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
    Negative Logits
     bre
    -0.04
    ĩ
    -0.04
     u
    -0.03
    u
    -0.02
    99
    -0.02
     dist
    -0.02
     distances
    -0.02
     read
    -0.02
     distance
    -0.02
    11
    -0.01
    POSITIVE LOGITS
    ter
    0.07
    120
    0.07
    70
    0.06
    35
    0.05
    55
    0.05
    60
    0.05
    ress
    0.05
    45
    0.05
    80
    0.05
    150
    0.05
    Activations Density 99.985%

    No Known Activations