© 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. 1689
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    first argument of instance methods

    python-code · gemini-2.5-flash-lite

    list item index (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
    reshold
    -0.05
     iter
    -0.04
    ateg
    -0.04
     steps
    -0.03
     while
    -0.03
    _step
    -0.03
     step
    -0.03
     run
    -0.03
     k
    -0.03
    und
    -0.03
    POSITIVE LOGITS
     parent
    0.03
    arent
    0.02
    _sum
    0.02
    _edges
    0.02
     next
    0.01
    ge
    0.01
    un
    0.01
    n
    0.01
     e
    0.01
    ((
    0.01
    Activations Density 85.501%

    No Known Activations