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

    Neuronpedia

    INDEX
    Explanations

    time and temporal references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.73
    ד
    0.69
    ä
    0.61
    \
    0.60
    <h2>
    0.57
    습니다
    0.57
     dialed
    0.57
     UCI
    0.57
     initially
    0.54
    ל
    0.53
    POSITIVE LOGITS
    h
    0.78
    ки
    0.72
     čas
    0.71
     Time
    0.62
    IA
    0.61
     시간
    0.60
    टाइम
    0.59
     К
    0.59
     Время
    0.59
    时间
    0.59
    Act Density 0.357%

    No Known Activations