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

    Neuronpedia

    INDEX
    Explanations

    expressing feelings, appreciation, or opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    0.93
    你
    0.85
    There
    0.80
    ı
    0.78
    ır
    0.75
    N
    0.75
    我们
    0.74
    我
    0.73
     in
    0.73
     (
    0.72
    POSITIVE LOGITS
    s
    1.23
    ς
    0.94
    ่า
    0.86
    ים
    0.80
    지
    0.75
    ی
    0.70
    sion
    0.68
    に
    0.68
    าน
    0.66
    ли
    0.65
    Act Density 0.043%

    No Known Activations