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

    Neuronpedia

    INDEX
    Explanations

    occurrences of structured data and programming syntax elements

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

    closing parenthesis or semicolon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.95
     للمعارف
    -0.93
    脚注の使い方
    -0.88
     ویکی‌آمباردا
    -0.84
     kasarigan
    -0.83
    Hentet
    -0.83
    :✨
    -0.76
     CreateTagHelper
    -0.74
    rungsseite
    -0.71
    IntoConstraints
    -0.71
    POSITIVE LOGITS
    Converted
    0.35
     "
    0.32
    nieren
    0.32
     Eto
    0.31
     editor
    0.30
     aras
    0.30
    ,
    0.30
     opt
    0.30
     conver
    0.29
     (
    0.28
    Act Density 0.066%

    No Known Activations