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

    Neuronpedia

    INDEX
    Explanations

    references to educational levels and grades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    school grades

    np_acts-logits-general · gemini-2.0-flash

    school grade levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    धिक
    -0.45
     leksikon
    -0.44
     teenager
    -0.43
     moelle
    -0.41
     高校
    -0.41
    arr
    -0.39
     Carr
    -0.38
    高校
    -0.38
    뜻
    -0.38
     ду
    -0.37
    POSITIVE LOGITS
     grade
    1.23
     grades
    1.12
     GRADE
    1.09
     Grade
    1.07
    Grade
    1.05
     Efq
    1.00
    grade
    0.98
     Grades
    0.92
    GRADE
    0.92
    Grades
    0.86
    Act Density 0.091%

    No Known Activations