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

    Neuronpedia

    INDEX
    Explanations

    college and academic subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    า
    0.80
    ين
    0.77
    ুল
    0.73
    ва
    0.69
    ا
    0.69
    ק
    0.67
    די
    0.67
    یم
    0.61
    ु
    0.59
    ुल
    0.58
    POSITIVE LOGITS
     College
    0.81
    -
    0.75
    College
    0.75
     COLLEGE
    0.72
    college
    0.67
     college
    0.66
    /
    0.63
    t
    0.61
     you
    0.59
    stance
    0.58
    Act Density 0.004%

    No Known Activations