© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 4134
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    'delimited' or 'as string'

    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
    in
    -0.07
    .in
    -0.05
    out
    -0.05
    ilename
    -0.05
    _file
    -0.05
    ilen
    -0.04
    .write
    -0.04
     file
    -0.04
    :-
    -0.04
    (filename
    -0.03
    POSITIVE LOGITS
    li
    0.07
    lot
    0.07
    =True
    0.04
    ab
    0.03
    gs
    0.03
    able
    0.03
    _and
    0.03
    co
    0.02
     cost
    0.02
     se
    0.02
    Activations Density 10.515%

    No Known Activations