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

    Neuronpedia

    INDEX
    Explanations

    being away or absent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    เศษ
    0.45
     حی
    0.36
     መጠ
    0.36
    <&
    0.36
    anken
    0.35
    osum
    0.35
    ᓱ
    0.35
    кансер
    0.35
     кандай
    0.34
    ղ
    0.34
    POSITIVE LOGITS
     away
    1.74
     Away
    1.54
    离开
    1.51
    離開
    1.50
    Away
    1.46
    离开了
    1.42
     AWAY
    1.41
     departure
    1.29
     absent
    1.25
    away
    1.23
    Act Density 0.025%

    No Known Activations