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

    Neuronpedia

    INDEX
    Explanations

    code-related constructs and function definitions

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

    "argument" or "parameter"

    np_acts-logits-general · gemini-2.0-flash

    function call arguments/parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jef
    -0.44
    Obrázky
    -0.43
    strix
    -0.42
    adaptiveStyles
    -0.42
     achieved
    -0.41
    StatusEnum
    -0.40
    Nationalité
    -0.40
    เก
    -0.40
     Normdatei
    -0.39
     dyr
    -0.39
    POSITIVE LOGITS
     arguments
    2.26
     argument
    2.16
    argument
    1.98
    arguments
    1.96
     args
    1.93
     Arguments
    1.92
     arg
    1.91
     Argument
    1.88
    Argument
    1.86
    Arguments
    1.84
    Act Density 0.563%

    No Known Activations