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

    Neuronpedia

    INDEX
    Explanations

    Miscellaneous information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     לשלם
    -0.07
    高く
    -0.07
     Bai
    -0.07
    อำเภ
    -0.07
    accountId
    -0.07
     Succ
    -0.06
    .backward
    -0.06
     king
    -0.06
    相关政策
    -0.06
    Curso
    -0.06
    POSITIVE LOGITS
     shutter
    0.07
    _HEALTH
    0.07
    バー
    0.07
    ット
    0.07
    agate
    0.06
    cripts
    0.06
     slave
    0.06
    ardin
    0.06
    ////
    0.06
    arily
    0.06
    Act Density 0.250%

    No Known Activations