© 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. 1616
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    isinstance check or type check

    python-code · gemini-2.5-flash-lite

    for loop identifier (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
     cols
    -0.04
     column
    -0.04
    .position
    -0.03
    _start
    -0.03
     lon
    -0.03
    01
    -0.02
     start
    -0.02
    _left
    -0.02
     left
    -0.02
     source
    -0.02
    POSITIVE LOGITS
     Create
    0.04
     Graph
    0.03
    stance
    0.03
     Initialize
    0.03
    0.02
     defaultdict
    0.02
    .graph
    0.02
     create
    0.02
    ax
    0.02
     [[
    0.02
    Activations Density 99.974%

    No Known Activations