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

    Neuronpedia

    INDEX
    Explanations

    pass to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    img
    0.64
     ನಡೆಸ
    0.63
    менение
    0.62
    V
    0.62
    with
    0.61
    words
    0.61
    まれた
    0.61
    что
    0.60
     करवाते
    0.60
    code
    0.59
    POSITIVE LOGITS
     into
    1.38
     kepada
    1.19
     Into
    1.09
     onto
    1.04
     إليه
    1.04
     इनटू
    1.02
    Into
    1.01
     إلى
    1.00
     INTO
    0.99
     unto
    0.91
    Act Density 0.518%

    No Known Activations