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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    假
    -0.07
    Cls
    -0.06
    ){
    -0.06
    olvimento
    -0.06
    letion
    -0.06
     Sociology
    -0.06
     butto
    -0.06
     ){
    -0.06
    bite
    -0.06
     changing
    -0.06
    POSITIVE LOGITS
    tv
    0.07
    ρή
    0.07
    ный
    0.07
    에서
    0.06
    рует
    0.06
    onn
    0.06
    ضافة
    0.06
     segmented
    0.06
    avatar
    0.06
     Loy
    0.06
    Act Density 0.000%

    No Known Activations