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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    生动
    -0.07
    .createElement
    -0.07
     poking
    -0.07
     outlet
    -0.07
    乐意
    -0.07
     экс
    -0.06
     jemand
    -0.06
     cake
    -0.06
    sek
    -0.06
     breakfast
    -0.06
    POSITIVE LOGITS
    힝
    0.08
    .ordinal
    0.07
     curing
    0.07
     unaffected
    0.07
    Argb
    0.07
    /dist
    0.07
     defines
    0.07
    .${
    0.07
    浰
    0.06
    unbind
    0.06
    Act Density 0.002%

    No Known Activations