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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cluster
    -0.08
    太阳能
    -0.07
    (Parameter
    -0.07
     CIM
    -0.07
     Elis
    -0.07
    Base
    -0.07
     Suzanne
    -0.06
     court
    -0.06
    总裁
    -0.06
    .Dependency
    -0.06
    POSITIVE LOGITS
    askan
    0.07
    初级
    0.07
     appel
    0.07
    роб
    0.07
    _NODES
    0.07
     PAY
    0.06
     unre
    0.06
     LV
    0.06
    🤸
    0.06
     Neg
    0.06
    Act Density 0.074%

    No Known Activations