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

    Neuronpedia

    INDEX
    Explanations

    water and beverages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    νες
    0.97
     धरती
    0.93
     UnityEngine
    0.91
     Москва
    0.90
    ди
    0.89
    н
    0.88
     lèvres
    0.87
     Київ
    0.86
    ння
    0.84
    ভাসের
    0.84
    POSITIVE LOGITS
    it
    1.02
    。
    0.90
    ir
    0.89
    하다
    0.86
     bersih
    0.83
    ⅰ
    0.83
    će
    0.82
    "
    0.82
    inplace
    0.80
    .$(
    0.80
    Act Density 0.002%

    No Known Activations