© 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. Residual Stream
    9. 7-RESID
    11. 887
    Prev
    Next
    INDEX
    Explanations

    converting to uppercase (negative activations)

    python-code · gemini-2.5-flash-lite

    ord function call

    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
    he
    -0.15
    hi
    -0.10
     l
    -0.03
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    !
    0.00
    POSITIVE LOGITS
    dex
    0.26
    se
    0.22
    ses
    0.21
    sed
    0.21
    ser
    0.20
    sible
    0.19
    si
    0.18
    ¹
    0.17
    ud
    0.15
    ke
    0.14
    Activations Density 92.481%

    No Known Activations