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

    Neuronpedia

    INDEX
    Explanations

    student

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    로
    1.30
    ات
    1.26
    是
    1.16
    ك
    1.16
    يب
    1.13
    อน
    1.13
    ও
    1.13
    لم
    1.11
    به
    1.11
    اب
    1.10
    POSITIVE LOGITS
     students
    1.35
     الطلاب
    1.27
     Students
    1.27
     STUDENTS
    1.27
     as
    1.26
     {
    1.20
    students
    1.19
    Students
    1.16
     학생
    1.16
     Student
    1.09
    Act Density 0.019%

    No Known Activations