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

    Neuronpedia

    INDEX
    Explanations

    continuous numerical values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Installation
    0.41
     AppDelegate
    0.40
     HttpResponse
    0.39
     Application
    0.39
    ပင်
    0.39
     Transplantation
    0.39
     Installing
    0.39
    သည့်
    0.38
     Veranstaltung
    0.38
     মন্
    0.38
    POSITIVE LOGITS
     प्रतिशत
    0.43
    差距
    0.41
     दशमलव
    0.41
    數量
    0.40
    ドル
    0.40
    数量
    0.40
     liczba
    0.39
     cuantos
    0.38
     być
    0.38
     percent
    0.38
    Act Density 0.004%

    No Known Activations