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

    Neuronpedia

    INDEX
    Explanations

    grants and funding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    牺
    -0.07
     Sorry
    -0.07
     timeStamp
    -0.07
    小白
    -0.07
    وير
    -0.06
    Probably
    -0.06
    ambia
    -0.06
     sleepy
    -0.06
    폴
    -0.06
    %s
    -0.06
    POSITIVE LOGITS
    CLK
    0.08
    _ws
    0.07
     unacceptable
    0.07
    )set
    0.07
     Numer
    0.07
    truth
    0.07
    -HT
    0.06
    __);↵
    0.06
    틈
    0.06
    に出
    0.06
    Act Density 0.067%

    No Known Activations