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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     UIColor
    0.86
     Со
    0.84
     Roy
    0.81
     ROY
    0.81
     oxide
    0.80
    тила
    0.78
    Roy
    0.77
     Welsh
    0.77
     voy
    0.76
     Oxide
    0.75
    POSITIVE LOGITS
    eterminate
    0.75
     comprehend
    0.68
    اسي
    0.67
    شت
    0.67
     comprehension
    0.66
    ాన్
    0.66
    未使用
    0.66
    自助
    0.65
    変わ
    0.65
    اعل
    0.65
    Act Density 0.000%

    No Known Activations