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

    Neuronpedia

    INDEX
    Explanations

    consequences or future states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जब
    0.38
    जब
    0.36
     when
    0.34
     wenn
    0.33
    如果你
    0.33
     যখন
    0.32
     utilizó
    0.32
     utilizamos
    0.31
     khi
    0.31
     nếu
    0.31
    POSITIVE LOGITS
    則
    0.34
    则
    0.34
     olacaktır
    0.33
    きっと
    0.32
     நிச்சயம்
    0.32
     будет
    0.31
    就會
    0.31
     allora
    0.30
    ówczas
    0.29
    then
    0.29
    Act Density 0.308%

    No Known Activations