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

    Neuronpedia

    INDEX
    Explanations

    ideas or actions done jointly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ו
    1.33
     و
    1.29
     ও
    1.10
    )。
    1.08
    𝙤
    1.00
     व
    0.97
     и
    0.97
     он
    0.94
     ч
    0.93
    );
    0.91
    POSITIVE LOGITS
    i
    1.58
    на
    1.45
    ა
    1.45
    는
    1.41
    트
    1.25
    ла
    1.23
    인
    1.20
    י
    1.18
    ات
    1.16
    त
    1.15
    Act Density 0.019%

    No Known Activations