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

    Neuronpedia

    INDEX
    Explanations

    writing parts or periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kullanımı
    0.57
     Linie
    0.50
     করিয়
    0.50
     မြ
    0.50
    來越
    0.49
     근
    0.49
     FULL
    0.49
     linh
    0.49
     രീതി
    0.49
     liners
    0.47
    POSITIVE LOGITS
    К
    0.61
    프
    0.56
    butt
    0.55
    마
    0.53
    এস
    0.51
    bags
    0.51
    道
    0.50
    Ф
    0.50
    平安
    0.49
    П
    0.49
    Act Density 0.000%

    No Known Activations