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

    Neuronpedia

    INDEX
    Explanations

    going

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kanya
    0.96
     poderá
    0.95
     Když
    0.94
    পিন
    0.93
     Почему
    0.93
     Saltar
    0.92
     سٹی
    0.91
    ўся
    0.91
     kommt
    0.91
     seep
    0.90
    POSITIVE LOGITS
    م
    1.11
    טה
    0.98
     destin
    0.87
    Innov
    0.86
    وم
    0.85
    ف
    0.84
    ९
    0.83
    بس
    0.82
    ли
    0.81
    াইবার
    0.81
    Act Density 0.000%

    No Known Activations