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

    Neuronpedia

    INDEX
    Explanations

    situations and abstract

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deepened
    0.44
     unpaid
    0.44
     nonzero
    0.41
    beforeend
    0.41
     আদি
    0.40
     वग
    0.40
    tration
    0.39
    虚拟
    0.39
    hedron
    0.39
    filter
    0.39
    POSITIVE LOGITS
     situazione
    0.61
     invito
    0.60
    方法は
    0.60
     существует
    0.60
     ситуация
    0.59
     если
    0.59
    事情
    0.58
     problemen
    0.57
     tragedia
    0.56
     удовольствием
    0.56
    Act Density 0.001%

    No Known Activations