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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    正式
    0.37
    emias
    0.36
    ్రో
    0.36
     gerade
    0.35
     bekommen
    0.35
     SPORTS
    0.35
     সন্ধ্যায়
    0.35
    िवी
    0.34
     ক্ষমা
    0.34
    prefixes
    0.34
    POSITIVE LOGITS
     once
    0.39
    rui
    0.39
     Caval
    0.38
     stopper
    0.38
    पर
    0.38
     octagon
    0.38
    mes
    0.37
     advising
    0.37
     سیر
    0.36
     sliding
    0.36
    Act Density 0.001%

    No Known Activations