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

    Neuronpedia

    INDEX
    Explanations

    half or fractional quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    E
    0.77
    0
    0.72
    x
    0.68
    8
    0.66
    どう
    0.65
    I
    0.64
    9
    0.62
    Μ
    0.59
    five
    0.59
    ל
    0.59
    POSITIVE LOGITS
     Half
    1.04
     half
    0.97
     نصف
    0.93
    Half
    0.80
     HALF
    0.79
    半
    0.79
    half
    0.78
    一半
    0.73
     nửa
    0.72
     অর্ধেক
    0.72
    Act Density 0.038%

    No Known Activations