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

    Neuronpedia

    INDEX
    Explanations

    lists of data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pentru
    0.44
     изменить
    0.44
    ющей
    0.43
     නැ
    0.42
    லாத
    0.41
     quirúrg
    0.41
     связано
    0.41
    ≃
    0.41
     tłumac
    0.40
     cosmological
    0.40
    POSITIVE LOGITS
    Wonder
    0.44
    াস
    0.41
    Graphic
    0.40
     Austro
    0.40
    θεση
    0.39
     لحظ
    0.38
    Doll
    0.38
    Detal
    0.38
    Identity
    0.38
    Conc
    0.38
    Act Density 0.082%

    No Known Activations