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

    Neuronpedia

    INDEX
    Explanations

    leaflets, brochures, pamphlets, booklets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    0.95
     to
    0.88
     was
    0.87
    บ
    0.87
     I
    0.84
     र
    0.84
     था
    0.84
    ม
    0.83
     by
    0.78
    ด
    0.78
    POSITIVE LOGITS
     leaflets
    1.41
     brochures
    1.33
     pamphlets
    1.16
     leaflet
    1.14
     booklets
    1.09
     flyers
    1.07
     сообщи
    1.06
     Booklet
    1.04
     booklet
    1.03
    leaflet
    1.03
    Act Density 0.002%

    No Known Activations