© 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. 2893
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    global keyword usage

    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
     <
    -0.03
    é
    -0.03
    æ
    -0.03
    å
    -0.03
    è
    -0.03
    ä
    -0.02
    ç
    -0.02
     >
    -0.02
    ã
    -0.02
     and
    -0.02
    POSITIVE LOGITS
     me
    0.05
    ()
    0.03
    ="
    0.02
    ='
    0.01
    =
    0.01
    !
    0.01
     |
    0.01
    .co
    0.01
    udoku
    0.01
    alc
    0.01
    Activations Density 40.591%

    No Known Activations