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

    Neuronpedia

    INDEX
    Explanations

    positive attributes or descriptors associated with experiences and evaluations

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

    Preceding words "how", "in", or "applications"

    np_acts-logits-general · gemini-2.0-flash

    applied to applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     continúas
    -0.57
    Hochspringen
    -0.49
    Архівовано
    -0.47
    𝟹
    -0.46
    sizeCache
    -0.41
    UnusedPrivate
    -0.41
     Garantía
    -0.40
    dropIfExists
    -0.38
    étation
    -0.38
    Semoga
    -0.37
    POSITIVE LOGITS
     informée
    0.61
    исленность
    0.49
    NewUrlParser
    0.46
     Normdatei
    0.43
    Biographie
    0.41
    delwed
    0.41
     NSError
    0.40
    avax
    0.39
     ویکی‌آمباردا
    0.39
    رشف
    0.39
    Act Density 0.070%

    No Known Activations