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

    Neuronpedia

    INDEX
    Explanations

    opposes weight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     qualcosa
    0.45
     seura
    0.45
     smooth
    0.44
     empr
    0.42
     pasar
    0.42
     coher
    0.41
     coherent
    0.41
     sapere
    0.41
    数の
    0.40
     এইসব
    0.40
    POSITIVE LOGITS
     지정
    0.40
    HK
    0.40
     খেল
    0.40
     Castillo
    0.40
    requested
    0.40
     orthopedic
    0.40
     मीडियम
    0.40
     खरीदा
    0.39
     আট
    0.39
     Ал
    0.38
    Act Density 0.007%

    No Known Activations