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

    Neuronpedia

    INDEX
    Explanations

    qualities of taste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ５
    0.76
    ي
    0.73
    、
    0.72
    신
    0.68
    ﻞ
    0.64
    ，
    0.61
     wymien
    0.61
    Очень
    0.61
     réessayer
    0.60
    ভি
    0.60
    POSITIVE LOGITS
    ch
    0.71
    il
    0.67
    iod
    0.66
     on
    0.65
    up
    0.64
     T
    0.62
    ed
    0.60
    sl
    0.59
    fd
    0.59
    FG
    0.59
    Act Density 0.016%

    No Known Activations