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

    Neuronpedia

    INDEX
    Explanations

    grading and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Branche
    0.72
     Mes
    0.71
     Realt
    0.71
     शिक्षित
    0.70
     సంగీ
    0.69
     Компания
    0.68
     τραγ
    0.67
     અનુભ
    0.66
     اللغه
    0.66
     cashmere
    0.65
    POSITIVE LOGITS
     grading
    2.15
     Grading
    2.06
     assignment
    2.03
     assignments
    1.98
     Assignments
    1.98
     Assignment
    1.98
    assignment
    1.95
    Assignment
    1.91
    Assignments
    1.87
     graded
    1.84
    Act Density 0.205%

    No Known Activations