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

    Neuronpedia

    INDEX
    Explanations

    your / possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pihaknya
    1.03
    彼は
    0.94
     kepad
    0.85
     dwóch
    0.81
     তাকে
    0.79
     nous
    0.78
    mselves
    0.77
     తాను
    0.76
    äle
    0.74
     그는
    0.73
    POSITIVE LOGITS
     your
    6.87
    your
    6.32
    Your
    5.94
     Your
    5.86
    你的
    5.72
    您的
    5.41
     YOUR
    5.13
     votre
    5.06
     вашего
    5.05
     вашей
    5.00
    Act Density 3.215%

    No Known Activations