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

    Neuronpedia

    INDEX
    Explanations

    day and hour formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    어로
    0.45
    طا
    0.45
    ⒈
    0.41
    ITECT
    0.40
    反馈
    0.40
    StarObject
    0.39
    ர்வ
    0.39
    愈
    0.39
    ircraft
    0.38
    痍
    0.38
    POSITIVE LOGITS
     Hours
    1.00
     hours
    0.97
     hour
    0.80
     Hour
    0.80
     ساعت
    0.80
    Hours
    0.79
    hours
    0.78
     morning
    0.77
     heures
    0.75
     Stunden
    0.73
    Act Density 0.012%

    No Known Activations