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

    Neuronpedia

    INDEX
    Explanations

    classic tropes and unique twists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fáciles
    0.89
     wanita
    0.82
    replaceable
    0.82
     faciles
    0.81
     útiles
    0.81
     sempurna
    0.80
     ediciones
    0.80
     estómago
    0.79
     улицы
    0.79
     rique
    0.77
    POSITIVE LOGITS
    ীয়
    0.83
    リオ
    0.63
    aturi
    0.62
    ｘ
    0.62
    ilene
    0.62
    कृत
    0.61
    Tiles
    0.61
     navController
    0.60
    sburg
    0.60
    وسی
    0.59
    Act Density 0.002%

    No Known Activations