© 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. 1763
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    comma in lists and dictionaries

    python-code · gemini-2.5-flash-lite

    `__name__ ==` (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
    -0.08
     tuple
    -0.05
    _counts
    -0.05
     dp
    -0.05
    _coords
    -0.04
    _position
    -0.04
     positions
    -0.04
    _positions
    -0.04
     If
    -0.04
     each
    -0.04
    POSITIVE LOGITS
    _tra
    0.03
    .↵
    0.02
    mple
    0.02
    init
    0.02
     tra
    0.02
    @
    0.02
    The
    0.02
     root
    0.02
     app
    0.02
     si
    0.02
    Activations Density 100.000%

    No Known Activations