© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 2984
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .split or .append (negative activations)

    python-code · gemini-2.5-flash-lite

    object method calls like .m.kdir or .m.atch

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .parent
    -0.05
     dfs
    -0.05
    ail
    -0.04
    gorithm
    -0.04
     algorithm
    -0.04
     !=
    -0.03
    jkstra
    -0.03
    enerate
    -0.03
     bre
    -0.03
     parent
    -0.03
    POSITIVE LOGITS
    .pop
    0.04
    param
    0.03
    args
    0.03
    arg
    0.02
     else
    0.02
     Par
    0.02
     par
    0.02
    ['
    0.02
    _par
    0.02
     min
    0.02
    Activations Density 88.907%

    No Known Activations