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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _Local
    -0.08
     CC
    -0.07
    (Constants
    -0.07
    叮嘱
    -0.07
     touted
    -0.07
     CB
    -0.07
    秘书长
    -0.07
    utive
    -0.07
     coats
    -0.07
    ⎨
    -0.07
    POSITIVE LOGITS
     Пр
    0.07
    民主
    0.07
    民族文化
    0.07
     Martinez
    0.06
    庞大
    0.06
     Fernandez
    0.06
    ipeline
    0.06
    _Result
    0.06
    elite
    0.06
     <:
    0.06
    Act Density 0.009%

    No Known Activations