© 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. 6484
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    attribute access (`.`) completion (negative activations)

    python-code · gemini-2.5-flash-lite

    min function call

    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
    heck
    -0.05
    is
    -0.05
     check
    -0.05
    .is
    -0.04
     Check
    -0.04
    are
    -0.04
     has
    -0.04
     count
    -0.03
    place
    -0.03
     valid
    -0.02
    POSITIVE LOGITS
    loat
    0.05
    .in
    0.05
     sys
    0.04
     float
    0.04
    99
    0.03
    .f
    0.02
     the
    0.02
     new
    0.02
     math
    0.02
    .m
    0.01
    Activations Density 96.561%

    No Known Activations