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

    Neuronpedia

    INDEX
    Explanations

    time and its variable t

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нәрсә
    0.41
    廨
    0.39
    徘
    0.39
    gın
    0.38
    㹮
    0.38
    ши
    0.38
    РА
    0.37
    Aware
    0.37
    Housing
    0.37
    GGG
    0.37
    POSITIVE LOGITS
     time
    1.70
     Time
    1.46
    時間
    1.41
    time
    1.38
     tiempo
    1.38
    时间
    1.36
     시간
    1.36
    Time
    1.34
     времени
    1.34
     시간을
    1.27
    Act Density 0.037%

    No Known Activations