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

    Neuronpedia

    INDEX
    Explanations

    common assumptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urian
    0.43
    áp
    0.41
    getUserMedia
    0.40
    natural
    0.39
    Lato
    0.39
     consensual
    0.39
    लाव
    0.39
    al
    0.37
    try
    0.37
     alami
    0.37
    POSITIVE LOGITS
     ತಪ್ಪ
    0.41
    спек
    0.41
     Pag
    0.40
    ക്ഷേ
    0.39
     dvs
    0.39
     anda
    0.38
     покупки
    0.38
    Pag
    0.37
     சேவை
    0.37
    ंपा
    0.37
    Act Density 0.001%

    No Known Activations