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

    Neuronpedia

    INDEX
    Explanations

    .ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    旋律
    -0.08
     withd
    -0.07
    &D
    -0.07
    %'↵
    -0.06
    卖掉
    -0.06
     fundraising
    -0.06
    =p
    -0.06
    甜美
    -0.06
     CHE
    -0.06
     Walk
    -0.06
    POSITIVE LOGITS
    <quote
    0.07
    罕
    0.07
    _preferences
    0.07
    /vendor
    0.07
     Eleven
    0.07
     notification
    0.07
     То
    0.06
     下
    0.06
    unifu
    0.06
     Contents
    0.06
    Act Density 0.003%

    No Known Activations