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

    Neuronpedia

    INDEX
    Explanations

    everyday life scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.94
    0.82
    TH
    0.76
    enst
    0.76
     sujet
    0.75
     have
    0.73
    Einzel
    0.72
    Tech
    0.71
    ing
    0.70
    D
    0.70
    POSITIVE LOGITS
    ни
    1.05
     rozwiąz
    0.95
     Everyday
    0.89
    спользу
    0.80
    ิ
    0.77
    rsquo
    0.76
    会
    0.75
    clientWidth
    0.75
    h
    0.75
    일상
    0.75
    Act Density 0.010%

    No Known Activations