© 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. 1629
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method call with underscore or 'd'

    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
    ion
    -0.18
    uple
    -0.11
     zip
    -0.10
     between
    -0.07
    ip
    -0.06
     base
    -0.01
     ra
    -0.01
    ari
    -0.01
    point
    -0.01
    _par
    -0.01
    POSITIVE LOGITS
    und
    0.06
    up
    0.06
    visited
    0.04
     visited
    0.04
    isited
    0.03
     the
    0.03
    rontier
    0.03
    on
    0.02
     dfs
    0.02
    queue
    0.02
    Activations Density 19.489%

    No Known Activations