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

    Neuronpedia

    INDEX
    Explanations

    least

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    前往
    -0.07
    为之
    -0.07
    kiye
    -0.07
     koń
    -0.07
     embarked
    -0.07
    ORB
    -0.07
     MEMBER
    -0.07
    proc
    -0.07
    云集
    -0.07
    complexType
    -0.07
    POSITIVE LOGITS
     вопрос
    0.07
    Finance
    0.07
     ......
    0.07
    晚报
    0.07
    我相信
    0.07
     anticip
    0.07
     daylight
    0.07
    )arg
    0.07
    aval
    0.06
    丫头
    0.06
    Act Density 0.011%

    No Known Activations