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

    Neuronpedia

    INDEX
    Explanations

    way to / manera de

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.79
    1
    0.76
    2
    0.73
    5
    0.71
    4
    0.68
    0
    0.68
    7
    0.66
     또는
    0.65
    8
    0.64
    6
    0.63
    POSITIVE LOGITS
     véhicule
    0.71
    產品
    0.64
     органі
    0.63
    絖
    0.63
     phẩm
    0.62
    获取
    0.61
    一组
    0.59
    ｏ
    0.59
     ابنائي
    0.58
    preprint
    0.58
    Act Density 0.003%

    No Known Activations