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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    展现
    -0.07
    (Server
    -0.07
    退役
    -0.07
     showcases
    -0.07
     inspiring
    -0.06
    UIViewController
    -0.06
     Foo
    -0.06
     initialState
    -0.06
     saint
    -0.06
     sustain
    -0.06
    POSITIVE LOGITS
    不懂
    0.08
    毛利率
    0.08
     Essen
    0.07
    ⌛
    0.07
    _hal
    0.07
    �
    0.07
    也是一个
    0.07
    嵋
    0.07
    瑝
    0.07
    .Exceptions
    0.07
    Act Density 0.007%

    No Known Activations