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

    Neuronpedia

    INDEX
    Explanations

    ordering/structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ryu
    -0.07
    都说
    -0.07
    nda
    -0.07
    Include
    -0.06
    你会发现
    -0.06
    _purchase
    -0.06
     goalie
    -0.06
    In
    -0.06
    衮
    -0.06
    国旗
    -0.06
    POSITIVE LOGITS
     مجموعة
    0.07
    .ForeColor
    0.07
     اكثر
    0.06
     אל
    0.06
    ใ
    0.06
    /services
    0.06
    表
    0.06
     материал
    0.06
    愉悦
    0.06
    筤
    0.06
    Act Density 0.023%

    No Known Activations