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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     nobody
    -0.07
     רפואי
    -0.07
    {}".
    -0.07
    两项
    -0.07
     searchTerm
    -0.07
    _tests
    -0.06
    בנות
    -0.06
     exclusive
    -0.06
    热带
    -0.06
    (Event
    -0.06
    POSITIVE LOGITS
     pong
    0.08
    �
    0.07
     生命周期
    0.07
    launcher
    0.07
    .pool
    0.07
    薪
    0.06
    uman
    0.06
     brill
    0.06
    unread
    0.06
    .ng
    0.06
    Act Density 0.192%

    No Known Activations