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

    Neuronpedia

    INDEX
    Explanations

    css properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     경우에는
    0.31
    typically
    0.29
     Supra
    0.28
    شاء
    0.27
     flaky
    0.26
    ಂದರೆ
    0.26
     oftentimes
    0.26
     beheld
    0.26
    OCc
    0.25
    ¹)
    0.25
    POSITIVE LOGITS
     terrorists
    0.28
    ટર
    0.28
     прове
    0.27
     терро
    0.27
    ες
    0.26
     людей
    0.26
    ارڈ
    0.26
     الجيش
    0.26
    0.25
     Ши
    0.25
    Act Density 0.014%

    No Known Activations