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

    Neuronpedia

    INDEX
    Explanations

    text structure markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﾓ
    0.40
    併
    0.38
     اتش
    0.36
     eingesetzt
    0.35
    প্রসঙ্গত
    0.35
    Bueno
    0.34
    så
    0.34
    Dann
    0.33
     ایپل
    0.33
    0.33
    POSITIVE LOGITS
    tained
    0.42
     akár
    0.41
     المتح
    0.41
     চারপাশে
    0.40
     მხოლოდ
    0.40
     Personalized
    0.40
     yalnızca
    0.40
    apunov
    0.39
    essing
    0.39
    imized
    0.38
    Act Density 0.006%

    No Known Activations