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

    Neuronpedia

    INDEX
    Explanations

    Disorder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .authorization
    -0.08
    ereum
    -0.07
    śmie
    -0.07
     гр
    -0.06
    郁
    -0.06
    ありますが
    -0.06
    弆
    -0.06
     yaşadığı
    -0.06
    热爱
    -0.06
    ﮒ
    -0.06
    POSITIVE LOGITS
    作为一个
    0.07
    etimes
    0.07
    oning
    0.06
    )obj
    0.06
    させて頂
    0.06
    数控
    0.06
     identifying
    0.06
     Clarke
    0.06
    一圈
    0.06
    :indexPath
    0.06
    Act Density 0.186%

    No Known Activations