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

    Neuronpedia

    INDEX
    Explanations

    one of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нем
    0.64
     diantaranya
    0.63
    não
    0.62
    ,:
    0.60
     هنا
    0.59
     $:
    0.58
     таки
    0.58
     něm
    0.57
    »:
    0.56
     aquí
    0.54
    POSITIVE LOGITS
     the
    0.84
    第一
    0.73
     erstes
    0.72
     your
    0.71
    最好的
    0.71
     our
    0.68
     my
    0.68
     najleps
    0.66
    的第一
    0.66
     first
    0.65
    Act Density 0.000%

    No Known Activations