© 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. 3299
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `is not None` or `as` or `[[`

    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
    .add
    -0.09
     <=
    -0.08
    ė
    -0.08
    .index
    -0.07
    ē
    -0.07
    ound
    -0.07
    |>
    -0.07
    .get
    -0.07
    .read
    -0.07
    .remove
    -0.06
    POSITIVE LOGITS
     re
    0.03
     we
    0.03
     exp
    0.03
     tra
    0.02
     None
    0.02
     per
    0.02
     en
    0.02
    None
    0.02
     get
    0.02
     al
    0.02
    Activations Density 70.314%

    No Known Activations