© 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. Residual Stream
    9. 7-RESID
    11. 1743
    Prev
    Next
    INDEX
    Explanations

    ch or le followed by ase or ases (negative activations)

    python-code · gemini-2.5-flash-lite

    comparison operators 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
    10
    -0.07
    44
    -0.05
    =
    -0.05
    16
    -0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    POSITIVE LOGITS
    ¾
    0.30
    cep
    0.27
    ates
    0.22
    ines
    0.19
    utes
    0.14
    ays
    0.14
    iz
    0.14
    fi
    0.13
    ses
    0.12
    ves
    0.12
    Activations Density 99.947%

    No Known Activations