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

    Neuronpedia

    INDEX
    Explanations

    place followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ра
    0.87
    ת
    0.76
    with
    0.75
    at
    0.74
    я
    0.70
    and
    0.69
    یم
    0.68
    한
    0.68
     ಎರಡ
    0.66
    3
    0.65
    POSITIVE LOGITS
    ’
    0.97
    p
    0.73
     I
    0.69
    ’,
    0.69
    houses
    0.68
    mma
    0.67
    ch
    0.66
    ,’
    0.65
     Faculdade
    0.63
    ক
    0.62
    Act Density 0.002%

    No Known Activations