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

    Neuronpedia

    INDEX
    Explanations

    throughout some period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    をした
    -1.66
    ccini
    -1.57
     viendo
    -1.55
    他に
    -1.53
     hablando
    -1.53
    认真
    -1.46
     poised
    -1.46
     when
    -1.44
     distur
    -1.41
    reszcie
    -1.41
    POSITIVE LOGITS
     fass
    1.63
     tuta
    1.63
    !（
    1.60
    During
    1.60
    Throughout
    1.59
     yaka
    1.57
    。"
    1.57
    ："
    1.53
    .~\
    1.52
     Châte
    1.52
    Act Density 0.020%

    No Known Activations