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

    Neuronpedia

    INDEX
    Explanations

    explicit, not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     understandably
    0.48
    ཊ
    0.44
     theatres
    0.44
    блиоте
    0.44
     gtk
    0.43
    ЕВ
    0.43
    Kaynak
    0.42
    梘
    0.41
    ﻓ
    0.41
    ੱਖ
    0.41
    POSITIVE LOGITS
     покры
    0.41
    !
    0.41
    ]=\
    0.38
     Athletic
    0.38
     ड्रेस
    0.37
     Allerg
    0.37
     phép
    0.36
     Biology
    0.36
     athletic
    0.36
     viêm
    0.35
    Act Density 0.018%

    No Known Activations