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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     modular
    0.37
    (//
    0.36
     flanking
    0.36
    bi
    0.35
     type
    0.34
     shielding
    0.34
     thrott
    0.34
    detect
    0.34
    ller
    0.34
     language
    0.33
    POSITIVE LOGITS
    今日は
    0.57
     Meetings
    0.56
    今日の
    0.55
     సమావేశ
    0.54
     Сегодня
    0.54
    Сегодня
    0.54
    Meetings
    0.54
     오늘의
    0.53
    Tuesday
    0.53
    Meeting
    0.53
    Act Density 0.004%

    No Known Activations