© 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. 1717
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment to 'a'

    python-code · gemini-2.5-flash-lite

    function call or assignment (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
    erge
    -0.06
    udoku
    -0.04
     update
    -0.04
    (len
    -0.03
    update
    -0.03
    adjac
    -0.02
    uccess
    -0.02
    aze
    -0.02
     conne
    -0.01
     par
    -0.01
    POSITIVE LOGITS
    py
    0.03
    No
    0.03
    dule
    0.03
    ner
    0.03
     n
    0.03
    .n
    0.02
    uil
    0.02
     nx
    0.02
    (N
    0.02
    num
    0.02
    Activations Density 99.978%

    No Known Activations