© 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. 1376
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    not in

    python-code · gemini-2.5-flash-lite

    call to `append` method (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
    mport
    -0.06
     (-
    -0.05
     (
    -0.04
     ('
    -0.04
     cols
    -0.04
    _map
    -0.03
     the
    -0.03
    _queue
    -0.03
    None
    -0.03
     ",
    -0.03
    POSITIVE LOGITS
     given
    0.03
    name
    0.02
     name
    0.02
    No
    0.02
    ilename
    0.02
     based
    0.02
    .name
    0.02
    ner
    0.02
    .n
    0.02
    _name
    0.02
    Activations Density 93.065%

    No Known Activations