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

    Neuronpedia

    INDEX
    Explanations

    leap year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ți
    1.01
    čné
    0.98
    бва
    0.98
    مین
    0.98
    ermek
    0.95
    詮
    0.93
    昆
    0.92
    屓
    0.92
     وأن
    0.91
    染
    0.91
    POSITIVE LOGITS
    I
    1.43
    ী
    1.18
    ्स
    1.17
    ร้าย
    1.16
    től
    1.15
    ामुळे
    1.13
    headlines
    1.12
     unfairly
    1.10
    ુ
    1.10
     unsett
    1.09
    Act Density 0.008%

    No Known Activations