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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .L
    -0.08
    (Class
    -0.07
    .visit
    -0.07
    (class
    -0.07
    萧
    -0.07
    (K
    -0.07
     Blvd
    -0.07
     phải
    -0.07
    협
    -0.07
    拳
    -0.07
    POSITIVE LOGITS
     MainWindow
    0.08
     magazines
    0.07
     puppies
    0.07
     głów
    0.07
     merchandise
    0.07
     deutsch
    0.07
     suicides
    0.07
    aires
    0.06
    丛书
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations