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

    Neuronpedia

    INDEX
    Explanations

    you can see or have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     becomes
    0.67
    becomes
    0.64
     diventa
    0.64
    成為
    0.61
     deviennent
    0.61
    变得
    0.61
    成为
    0.59
     становятся
    0.59
     становится
    0.57
     convertirse
    0.57
    POSITIVE LOGITS
     expecting
    0.52
     expect
    0.42
     thấy
    0.42
    把
    0.41
    将
    0.41
    可以将
    0.40
     achieve
    0.38
    няў
    0.38
    iget
    0.38
    ريط
    0.38
    Act Density 0.013%

    No Known Activations