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

    Neuronpedia

    INDEX
    Explanations

    real and actual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ুষ
    0.40
     Epp
    0.36
    laquo
    0.35
    ণিজ্য
    0.34
    ucher
    0.34
    似乎
    0.34
    numerator
    0.34
     EXCEPT
    0.32
    ྜ
    0.32
    imètre
    0.32
    POSITIVE LOGITS
     real
    2.77
     실제
    2.72
     реа
    2.63
     actual
    2.61
    实际
    2.50
    実際の
    2.48
     वास्तविक
    2.41
    actual
    2.39
    真实
    2.30
    實際
    2.30
    Act Density 0.075%

    No Known Activations