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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    usra
    -0.08
    _identifier
    -0.07
    ợi
    -0.07
     discovering
    -0.07
     Gulf
    -0.07
    _sock
    -0.07
    卫健
    -0.07
    防止
    -0.07
    鸶
    -0.07
    批发
    -0.06
    POSITIVE LOGITS
     deport
    0.07
     Sleeping
    0.07
     เช
    0.07
     //}↵
    0.07
    .Do
    0.07
     Dorm
    0.06
    แสด
    0.06
    Do
    0.06
    :↵↵↵↵↵↵
    0.06
    شروط
    0.06
    Act Density 0.002%

    No Known Activations