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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -scalable
    -0.07
    nd
    -0.07
     tan
    -0.07
     mãi
    -0.06
    �
    -0.06
    瞫
    -0.06
    �
    -0.06
    atLng
    -0.06
    :Is
    -0.06
    늙
    -0.06
    POSITIVE LOGITS
     timing
    0.08
    _condition
    0.07
     translation
    0.07
    /comment
    0.07
    _break
    0.07
     ]↵
    0.07
    탶
    0.07
     boxes
    0.07
    百合
    0.06
    ASSERT
    0.06
    Act Density 0.002%

    No Known Activations