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

    Neuronpedia

    INDEX
    Explanations

    sex organs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ু
    0.78
     प्रतिबंध
    0.77
    大规模
    0.74
     如
    0.71
     predmet
    0.71
    responsible
    0.70
    unce
    0.70
    ose
    0.69
    孭
    0.69
     Apakah
    0.68
    POSITIVE LOGITS
     endere
    0.93
    на
    0.92
     монасты
    0.91
    dır
    0.91
     Erit
    0.90
     Elo
    0.89
     humanist
    0.89
     henna
    0.88
     eels
    0.88
    ten
    0.86
    Act Density 0.000%

    No Known Activations