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

    Neuronpedia

    INDEX
    Explanations

    teacher

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िको
    0.45
    ตะ
    0.43
    ্যার
    0.41
     αντι
    0.40
    lanır
    0.40
     описа
    0.40
     ทํา
    0.40
    簱
    0.40
     thuê
    0.39
     широкий
    0.39
    POSITIVE LOGITS
     Teachers
    1.09
     Teacher
    1.03
    Teacher
    1.00
    Teachers
    0.98
     teacher
    0.94
     teachers
    0.93
    teacher
    0.93
    老师
    0.88
     учитель
    0.83
    teachers
    0.81
    Act Density 0.004%

    No Known Activations