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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    低い
    0.59
    lowest
    0.58
    smallest
    0.54
    低的
    0.53
     Lowest
    0.50
     rendah
    0.49
    ານ
    0.48
    決して
    0.48
    小さい
    0.47
     않으면
    0.47
    POSITIVE LOGITS
     more
    5.56
     lebih
    4.53
    more
    4.50
     более
    4.41
    更多
    4.41
     más
    4.28
     More
    4.19
     MORE
    4.16
    More
    4.13
     mehr
    4.13
    Act Density 1.412%

    No Known Activations