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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     distributions
    -0.07
    дар
    -0.07
    istr
    -0.07
    trim
    -0.07
     enthusiast
    -0.07
    .leave
    -0.07
    拇指
    -0.07
     unm
    -0.07
    	distance
    -0.07
     hiểm
    -0.07
    POSITIVE LOGITS
     brit
    0.08
    .bg
    0.07
    ystick
    0.07
     Украин
    0.07
    ToJson
    0.06
    埆
    0.06
    쁨
    0.06
    %@",
    0.06
    }'.
    0.06
    Cs
    0.06
    Act Density 0.019%

    No Known Activations