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

    Neuronpedia

    INDEX
    Explanations

    icon and moss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    する
    0.80
    ை
    0.77
    ة
    0.74
    o
    0.72
     was
    0.71
    in
    0.70
    ва
    0.69
    い
    0.69
    é
    0.68
    ing
    0.66
    POSITIVE LOGITS
    N
    0.74
    Đặt
    0.63
     I
    0.62
    Giá
    0.60
    TAK
    0.59
    gahan
    0.59
    Nh
    0.59
    дной
    0.59
    baixo
    0.57
    ठ
    0.57
    Act Density 0.000%

    No Known Activations