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

    Neuronpedia

    INDEX
    Explanations

    leaving or returning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    用到
    0.86
     একসাথে
    0.85
     একত্রে
    0.82
     맞춰
    0.81
     একত্রিত
    0.80
    داخل
    0.80
     সর্বপ্রথম
    0.80
    制定
    0.79
    Reduction
    0.77
     באמצעות
    0.76
    POSITIVE LOGITS
    离开
    1.51
    離開
    1.47
     exit
    1.46
     leave
    1.45
    exit
    1.41
    离开了
    1.38
     leaving
    1.37
     departure
    1.32
     retreating
    1.32
     Leave
    1.28
    Act Density 0.145%

    No Known Activations