© 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. 1880
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    csv.DictReader or csv.DictWriter

    python-code · gemini-2.5-flash-lite

    list index or slice (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
    .name
    -0.02
    .id
    -0.02
    _idx
    -0.02
    dex
    -0.02
    .position
    -0.01
    _index
    -0.01
     op
    -0.01
    <|
    -0.01
    _coords
    -0.01
    _position
    -0.01
    POSITIVE LOGITS
    valid
    0.01
    sible
    0.01
    22
    0.01
    ab
    0.01
     shortest
    0.01
    (n
    0.01
    _tra
    0.01
     tra
    0.00
    _g
    0.00
     ex
    0.00
    Activations Density 100.000%

    No Known Activations