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

    Neuronpedia

    INDEX
    Explanations

    locate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     I
    -0.07
     W
    -0.07
    FN
    -0.07
     Oz
    -0.07
    ＝
    -0.06
     gains
    -0.06
    ]↵
    -0.06
     dataList
    -0.06
    _valid
    -0.06
    raction
    -0.06
    POSITIVE LOGITS
    �
    0.07
    .ApplyResources
    0.07
     guidelines
    0.06
    丧
    0.06
    Ӥ
    0.06
    櫆
    0.06
    ','".$
    0.06
    曼联
    0.06
    azines
    0.06
     компью
    0.06
    Act Density 0.008%

    No Known Activations