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

    Neuronpedia

    INDEX
    Explanations

    term that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     उपयोगकर्ता
    0.57
     सीधे
    0.57
     แต่
    0.52
     यूजर
    0.50
     옆
    0.47
     непосредственно
    0.47
     Doğ
    0.46
     akkor
    0.46
     echter
    0.46
     своей
    0.46
    POSITIVE LOGITS
    感が
    0.42
    ยาน
    0.41
    用了
    0.41
    大型
    0.40
    iminary
    0.39
     glazing
    0.39
     stage
    0.39
     blamed
    0.38
    involved
    0.38
     hosted
    0.38
    Act Density 0.002%

    No Known Activations