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

    Neuronpedia

    INDEX
    Explanations

    introducing examples with such as

    np_acts-logits-general · gemini-2.5-flash-lite

    examples such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.66
    とおり
    0.60
    น
    0.59
    ่
    0.57
     saddhim
    0.55
     всі
    0.54
     সংখ্য
    0.53
    ре
    0.52
     rupani
    0.50
    ુ
    0.50
    POSITIVE LOGITS
    (
    0.85
     of
    0.69
    of
    0.67
    ,
    0.66
     to
    0.61
    <
    0.58
    اج
    0.56
    اض
    0.51
    اً
    0.51
     was
    0.50
    Act Density 0.083%

    No Known Activations