© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4815
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    comma or closing parenthesis (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment statement

    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
    ault
    -0.04
     default
    -0.04
     Def
    -0.04
     it
    -0.04
    def
    -0.02
    for
    -0.01
     for
    -0.01
     while
    -0.01
    R
    -0.01
    E
    -0.01
    POSITIVE LOGITS
                ↵
    0.03
            ↵
    0.03
                    ↵
    0.03
        ↵
    0.03
     print
    0.02
    print
    0.02
     :
    0.02
    rint
    0.01
    0.01
    .write
    0.01
    Activations Density 62.396%

    No Known Activations