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

    Neuronpedia

    INDEX
    Explanations

    foreign characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كتبت
    0.42
    म्मेदारी
    0.41
    ೭
    0.40
    何か
    0.40
    валися
    0.40
    ገድ
    0.39
    very
    0.39
    تع
    0.39
    coffee
    0.39
    ขึ้น
    0.38
    POSITIVE LOGITS
     millennia
    0.42
     খুঁ
    0.38
    版权
    0.38
    asic
    0.38
     [&](
    0.37
    徽
    0.37
     осно
    0.36
     identically
    0.36
    替换
    0.36
    丘
    0.36
    Act Density 0.000%

    No Known Activations