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

    Neuronpedia

    INDEX
    Explanations

    us

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     themselves
    0.67
    yourself
    0.53
    mselves
    0.48
     আমাকে
    0.47
    在我
    0.47
     yourself
    0.47
    讓我
    0.44
     comigo
    0.44
    わたし
    0.44
     मुझे
    0.43
    POSITIVE LOGITS
     ourselves
    1.04
     نحن
    1.00
     جميعا
    0.88
    如果我们
    0.85
     mortals
    0.82
     છીએ
    0.80
     kaldığımız
    0.77
     humans
    0.76
     هستیم
    0.71
    当我们
    0.70
    Act Density 0.011%

    No Known Activations