Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    programming language syntax related to function definitions and variable declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX and TikZ code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kr
    -0.28
     Federal
    -0.28
     socios
    -0.27
    честву
    -0.27
    verifyException
    -0.26
    php
    -0.26
    endenza
    -0.26
    copyOf
    -0.26
    GraphicsUnit
    -0.25
    d
    -0.25
    POSITIVE LOGITS
     makeStyles
    0.78
     Савезне
    0.69
     ujednoznacz
    0.67
     autorytatywna
    0.66
    InjectAttribute
    0.66
     estekak
    0.65
    newcommand
    0.64
    SourceChecksum
    0.62
    OGND
    0.61
    ArgumentParser
    0.59
    Act Density 0.002%

    No Known Activations