© 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. 1338
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    colon or closing parenthesis

    python-code · gemini-2.5-flash-lite

    `(` followed by argument (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
    (se
    -0.05
     self
    -0.03
    ut
    -0.03
    ['
    -0.02
    th
    -0.02
     th
    -0.02
     c
    -0.02
    "↵↵
    -0.02
    def
    -0.02
    }")<|
    -0.02
    POSITIVE LOGITS
    enerate
    0.04
    it
    0.03
    uration
    0.03
    ight
    0.03
    **
    0.03
     **
    0.02
    irst
    0.02
    ay
    0.02
    ield
    0.02
    rib
    0.02
    Activations Density 69.017%

    No Known Activations