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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Mueller
    -0.08
    :start
    -0.07
    染
    -0.07
     북
    -0.07
    .ol
    -0.07
    _INT
    -0.07
     darling
    -0.07
     definitely
    -0.07
     Coastal
    -0.07
     coast
    -0.07
    POSITIVE LOGITS
     KG
    0.07
    蛊
    0.07
     Dresses
    0.07
     cams
    0.07
    ClearColor
    0.07
    /'↵↵
    0.07
    宣传片
    0.07
     HP
    0.06
     ******************************************************************************↵
    0.06
    平凡
    0.06
    Act Density 0.003%

    No Known Activations