© 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. 1751
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment or parameter separator

    python-code · gemini-2.5-flash-lite

    string method calls (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
    .position
    -0.05
    _coords
    -0.03
    _position
    -0.03
    sen
    -0.03
     positions
    -0.03
    _loc
    -0.03
     coordinates
    -0.03
     Get
    -0.02
    hildren
    -0.02
    (st
    -0.02
    POSITIVE LOGITS
     is
    0.06
    .is
    0.06
     *
    0.05
    *
    0.05
     **
    0.04
    is
    0.04
    **
    0.04
     has
    0.04
    get
    0.03
     {}↵↵
    0.03
    Activations Density 99.990%

    No Known Activations