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

    Neuronpedia

    INDEX
    Explanations

    Government entities and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    1.08
     are
    0.98
    其他
    0.94
    ため
    0.90
    كيف
    0.89
    م
    0.88
    的
    0.87
    ا۔
    0.86
    któ
    0.82
    知道
    0.80
    POSITIVE LOGITS
    is
    1.19
    <0x80>
    0.94
    0
    0.87
     inhalation
    0.86
    (
    0.82
    ти
    0.80
    ’
    0.80
    *
    0.78
    л
    0.77
    an
    0.77
    Act Density 0.019%

    No Known Activations