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

    Neuronpedia

    INDEX
    Explanations

    because or signaling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     다양한
    0.47
    삶
    0.46
     ਜਾ
    0.45
     создания
    0.44
    לי
    0.44
    ᓯ
    0.44
    ཌ
    0.44
    בי
    0.43
     diverses
    0.43
     создавать
    0.43
    POSITIVE LOGITS
     because
    0.52
     porque
    0.45
     immediately
    0.44
     perché
    0.42
     Because
    0.42
     indicator
    0.42
    因为
    0.42
     BECAUSE
    0.42
     signaling
    0.41
     Çünkü
    0.41
    Act Density 0.037%

    No Known Activations