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

    Neuronpedia

    INDEX
    Explanations

    and... does

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     covenant
    0.81
     الانترنت
    0.74
     لبنان
    0.73
     పుస్త
    0.73
    網絡
    0.73
    Enjoy
    0.73
    銀行
    0.72
     WENO
    0.72
     Economies
    0.72
    coronavirus
    0.72
    POSITIVE LOGITS
     הוא
    0.75
     vardı
    0.68
    它
    0.60
    他对
    0.60
     semuanya
    0.58
     સ્પ
    0.58
    சம்
    0.57
    شا
    0.57
     सपा
    0.57
     she
    0.56
    Act Density 0.040%

    No Known Activations