© 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. 6928
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    indexing list elements (negative activations)

    python-code · gemini-2.5-flash-lite

    the `or` keyword in conditional statements

    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
     },↵
    -0.05
    .parent
    -0.04
     !=
    -0.04
     ]↵
    -0.04
     def
    -0.03
     True
    -0.03
     {'
    -0.03
     {"
    -0.03
    |
    -0.03
     """↵
    -0.03
    POSITIVE LOGITS
     <
    0.08
     if
    0.06
    <
    0.05
     >
    0.05
     or
    0.05
    lambda
    0.04
    (str
    0.04
     while
    0.04
     If
    0.04
    .pop
    0.03
    Activations Density 99.101%

    No Known Activations