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

    Neuronpedia

    INDEX
    Explanations

    absolutely not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    보다는
    0.54
    未必
    0.51
    不太
    0.50
     אבל
    0.49
     però
    0.48
     อาจ
    0.47
     പക്ഷേ
    0.47
    但也
    0.46
     potrebbe
    0.45
     অবশ্য
    0.44
    POSITIVE LOGITS
     assolutamente
    0.76
     absolutamente
    0.75
     ANY
    0.71
     NEVER
    0.66
     NOTHING
    0.64
     ONLY
    0.63
     ANYTHING
    0.61
     ALWAYS
    0.59
     asla
    0.57
     absolument
    0.56
    Act Density 0.482%

    No Known Activations