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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ли
    0.89
     groves
    0.80
    ছেন
    0.77
    র
    0.75
     Dragons
    0.73
     Arrows
    0.73
     Cartesian
    0.71
     агент
    0.71
    смотря
    0.71
     Def
    0.70
    POSITIVE LOGITS
     glav
    0.84
     devlet
    0.84
    waż
    0.81
     lutte
    0.80
     mulig
    0.79
     vutta
    0.78
    啕
    0.77
     doar
    0.77
    比如
    0.76
    टिंग
    0.76
    Act Density 0.000%

    No Known Activations