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

    Neuronpedia

    INDEX
    Explanations

    prepositions like 'to'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.57
    ing
    0.54
     biais
    0.51
    in
    0.47
    n
    0.45
    ain
    0.44
    ina
    0.43
    eren
    0.42
    ie
    0.42
    iere
    0.42
    POSITIVE LOGITS
     oatmeal
    0.49
     ایسی
    0.46
     문제는
    0.46
    Dichloro
    0.44
    訣
    0.44
    мети
    0.44
     viviendas
    0.43
     a
    0.43
     रकम
    0.43
    стом
    0.43
    Act Density 0.079%

    No Known Activations