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

    Neuronpedia

    INDEX
    Explanations

    _library

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beide
    -0.07
     Fork
    -0.06
    =wx
    -0.06
     afternoon
    -0.06
     dock
    -0.06
    地址
    -0.06
    datetime
    -0.06
    술
    -0.06
    ，要
    -0.06
     giveaways
    -0.06
    POSITIVE LOGITS
    "}}>↵
    0.07
     участие
    0.07
    ?>/
    0.07
     Astroph
    0.07
    _PIN
    0.07
    ��
    0.07
     tenure
    0.06
     }>
    0.06
     }</
    0.06
     *)[
    0.06
    Act Density 0.008%

    No Known Activations