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

    Neuronpedia

    INDEX
    Explanations

    user interface elements and their interactive components

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

    HTML tags and various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __*/
    -0.80
    ArgsConstructor
    -0.71
    ConstraintMaker
    -0.71
    Gön
    -0.70
     يتيمه
    -0.69
     المعيارى
    -0.69
    الحياه
    -0.67
    ContentAsync
    -0.67
    LookAnd
    -0.66
    parsedMessage
    -0.66
    POSITIVE LOGITS
     finnes
    0.33
    Pozdrawiam
    0.33
     Púb
    0.32
     nettsted
    0.29
    baiki
    0.29
     conférences
    0.28
     enfans
    0.27
     ministres
    0.26
     antaranya
    0.26
    ambién
    0.26
    Act Density 0.018%

    No Known Activations