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

    Neuronpedia

    INDEX
    Explanations

    parentheses ()

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Estou
    0.98
     Mã
    0.89
    estabelecimento
    0.88
     estou
    0.88
    Jangan
    0.84
    Voir
    0.84
     Tính
    0.83
     Atual
    0.83
    tahun
    0.82
     Não
    0.81
    POSITIVE LOGITS
    ات
    0.83
    ل
    0.79
     sprint
    0.78
    ع
    0.78
    ‌اند
    0.77
    ку
    0.76
    s
    0.73
     spanning
    0.72
    न
    0.70
    ਅ
    0.70
    Act Density 0.000%

    No Known Activations