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

    Neuronpedia

    INDEX
    Explanations

    not or rarely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     posso
    0.43
     passato
    0.41
     complicated
    0.40
    વવા
    0.40
     einigen
    0.40
    不久
    0.38
     fratt
    0.37
    tere
    0.37
     improbable
    0.37
    基本
    0.36
    POSITIVE LOGITS
     during
    0.66
     During
    0.63
    during
    0.63
     through
    0.62
     именно
    0.62
     Through
    0.60
     через
    0.59
    那些
    0.57
     when
    0.57
    During
    0.57
    Act Density 0.008%

    No Known Activations