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

    Neuronpedia

    INDEX
    Explanations

    顺

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    activated
    -0.08
     রেখে
    -0.07
     ترك
    -0.07
     maintaining
    -0.07
     enclosing
    -0.07
    depart
    -0.07
     =(
    -0.07
     തമ്മ
    -0.07
    :(
    -0.07
     PV
    -0.07
    POSITIVE LOGITS
     好运
    0.11
     réussir
    0.10
    顺
    0.09
     hassle
    0.09
    畅
    0.09
     موفق
    0.09
     如意
    0.09
    捷
    0.09
     succes
    0.09
     सफलता
    0.09
    Act Density 0.001%

    No Known Activations