© 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. 7750
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list elements as numbers (negative activations)

    python-code · gemini-2.5-flash-lite

    boolean variable comparison

    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
    udoku
    -0.03
    lambda
    -0.02
    (str
    -0.02
    aze
    -0.01
    er
    -0.01
    |
    -0.01
     par
    -0.01
     pass
    -0.01
    (int
    -0.01
    at
    -0.01
    POSITIVE LOGITS
     continue
    0.02
    =None
    0.02
    ='
    0.02
    =True
    0.02
     initial
    0.02
    ="
    0.02
    uild
    0.01
    ),↵
    0.01
     return
    0.01
     con
    0.01
    Activations Density 95.784%

    No Known Activations