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

    Neuronpedia

    INDEX
    Explanations

    rounding numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.55
    u
    0.45
    ς
    0.45
    ا
    0.44
    a
    0.44
    า
    0.44
    ์
    0.43
    ים
    0.42
    на
    0.41
    i
    0.41
    POSITIVE LOGITS
    Гор
    0.37
    2
    0.37
    Он
    0.37
    Опера
    0.35
    Fiction
    0.34
    Для
    0.34
     Ashland
    0.34
    Created
    0.34
    Пре
    0.33
    Fill
    0.33
    Act Density 0.001%

    No Known Activations