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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     trims
    0.47
     upt
    0.46
     fibrosis
    0.45
     it
    0.44
     about
    0.44
    itul
    0.43
     trim
    0.43
     बाग
    0.42
     r
    0.42
     l
    0.42
    POSITIVE LOGITS
     ඔබේ
    0.60
     شما
    0.56
     თქვენ
    0.55
     আপনার
    0.55
     သင်
    0.54
     ഒരു
    0.52
     உங்கள்
    0.52
     您
    0.52
     நீங்கள்
    0.51
    Mât
    0.51
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.