© 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. 2-MLP
    11. 3185
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    range()

    python-code · gemini-2.5-flash-lite

    max = 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
    udok
    -0.12
    lauses
    -0.10
    dom
    -0.10
    ateg
    -0.10
    ariables
    -0.09
    lause
    -0.09
    udoku
    -0.08
    straints
    -0.07
     var
    -0.07
    rect
    -0.07
    POSITIVE LOGITS
    zero
    0.08
    gest
    0.06
    over
    0.06
     char
    0.05
    ]][
    0.05
    term
    0.05
                ↵
    0.04
     representing
    0.04
    inal
    0.04
    ash
    0.04
    Activations Density 100.000%

    No Known Activations