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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    勇于
    -0.08
     originates
    -0.07
    recommend
    -0.07
     N
    -0.07
    🏆
    -0.07
     ALIGN
    -0.06
    ༚
    -0.06
    شرق
    -0.06
    .YELLOW
    -0.06
    equip
    -0.06
    POSITIVE LOGITS
    储蓄
    0.08
    flutter
    0.07
    .toolbox
    0.07
     Driver
    0.07
    obody
    0.07
    атор
    0.07
     Серг
    0.07
     karakter
    0.07
     метро
    0.07
     машин
    0.07
    Act Density 0.029%

    No Known Activations