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

    Neuronpedia

    INDEX
    Explanations

    years/numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     measure
    -0.08
     moderne
    -0.08
     modernes
    -0.08
     Toll
    -0.08
    ttle
    -0.08
     rigid
    -0.07
     finer
    -0.07
     histórias
    -0.07
     आधुनिक
    -0.07
     الحديث
    -0.07
    POSITIVE LOGITS
     sophomore
    0.12
     ವರ್ಷದ
    0.12
    semester
    0.11
     tenure
    0.11
     freshman
    0.10
     Semester
    0.10
    Semester
    0.10
    숙
    0.10
     semester
    0.10
     વિદ્યાર્થી
    0.10
    Act Density 0.034%

    No Known Activations