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

    Neuronpedia

    INDEX
    Explanations

    into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yanında
    0.73
    在使用
    0.62
    కోండి
    0.61
    źnie
    0.61
    는지
    0.60
    နှုန်း
    0.60
     переви
    0.59
     yerde
    0.59
    കൾ
    0.59
     работе
    0.58
    POSITIVE LOGITS
     into
    5.93
    into
    5.14
    Into
    5.07
     Into
    5.01
     INTO
    4.42
     इनटू
    4.14
     vào
    4.04
     onto
    3.76
    onto
    2.69
     nto
    2.43
    Act Density 0.935%

    No Known Activations