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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Without
    -0.07
     Shah
    -0.06
    歡迎
    -0.06
    出国留学
    -0.06
    /tree
    -0.06
    可能性
    -0.06
    .GetUser
    -0.06
     Species
    -0.06
    UTOR
    -0.06
     Frank
    -0.06
    POSITIVE LOGITS
     EditText
    0.07
    منظومة
    0.07
     stabilize
    0.07
     ברור
    0.07
     abnormal
    0.07
    城管
    0.07
    строй
    0.06
    زمة
    0.06
    终端
    0.06
    bay
    0.06
    Act Density 0.013%

    No Known Activations