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

    Neuronpedia

    INDEX
    Explanations

    words ending with "up"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र
    1.48
    er
    1.06
    erver
    1.06
     quyết
    0.97
    Укупно
    0.96
     graham
    0.93
    ಿ
    0.92
    ন্তন
    0.89
     ind
    0.89
    iest
    0.89
    POSITIVE LOGITS
    ﺩ
    1.03
     namely
    1.01
     اللهم
    0.94
    unin
    0.94
    REME
    0.93
    AC
    0.91
    driving
    0.91
    khane
    0.88
    शुदा
    0.88
     govori
    0.88
    Act Density 0.193%

    No Known Activations