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

    Neuronpedia

    INDEX
    Explanations

    all the way to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.87
    ती
    0.78
    q
    0.74
    য়াস
    0.73
     diocese
    0.71
    ANG
    0.70
    කාර
    0.68
     rapidez
    0.68
     રાશિફળ
    0.67
    N
    0.67
    POSITIVE LOGITS
    to
    0.93
    na
    0.80
    前的
    0.80
     مايو
    0.79
     ل
    0.76
     від
    0.76
    ス
    0.76
    are
    0.74
    ان
    0.74
     dechlorination
    0.72
    Act Density 0.018%

    No Known Activations