© 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. 1642
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .p attribute access

    python-code · gemini-2.5-flash-lite

    else keyword (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
     between
    -0.05
    loat
    -0.05
    (s
    -0.04
    S
    -0.02
    _s
    -0.02
    sw
    -0.02
    li
    -0.02
    lot
    -0.02
     *
    -0.01
    im
    -0.01
    POSITIVE LOGITS
     dfs
    0.07
    gorithm
    0.05
     algorithm
    0.05
    jkstra
    0.05
     bre
    0.04
     Find
    0.04
     search
    0.04
    _search
    0.04
     heapq
    0.04
    .path
    0.04
    Activations Density 29.075%

    No Known Activations