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

    Neuronpedia

    INDEX
    Explanations

    various categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    д
    1.27
    ো
    1.16
    า
    1.15
    n
    1.14
    तया
    1.11
     ๆ
    1.10
    ि
    1.10
     Trebuie
    1.10
    ש
    1.09
    י
    1.08
    POSITIVE LOGITS
     including
    0.94
     ([
    0.91
    À
    0.91
     despite
    0.90
     ((
    0.89
    <unused474>
    0.88
     пала
    0.87
    ová
    0.86
     subjected
    0.84
     steadily
    0.84
    Act Density 0.066%

    No Known Activations