© 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. 1295
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    inside function call (

    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
    .values
    -0.01
     for
    -0.01
    class
    -0.01
    <|
    -0.01
     cur
    -0.01
    .con
    -0.01
    red
    -0.01
     with
    -0.00
    1
    -0.00
     is
    -0.00
    POSITIVE LOGITS
    (range
    0.03
    range
    0.03
     range
    0.02
     {}↵
    0.02
    _range
    0.02
     {↵
    0.02
    ↵
    0.02
        ↵
    0.01
     },↵
    0.01
    ]↵
    0.01
    Activations Density 35.565%

    No Known Activations