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

    Neuronpedia

    INDEX
    Explanations

    Russian grammatical endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ات
    0.86
    ﺭ
    0.80
    其他
    0.79
    '
    0.78
     Italians
    0.77
    ان
    0.76
    ال
    0.76
     doux
    0.75
    者に
    0.75
    ει
    0.73
    POSITIVE LOGITS
    ur
    0.89
    ing
    0.88
    ๔
    0.88
    ä
    0.86
    ة
    0.75
    ni
    0.75
    nu
    0.75
    be
    0.75
     be
    0.74
    ни
    0.74
    Act Density 0.099%

    No Known Activations