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

    Neuronpedia

    INDEX
    Explanations

    ized/itized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aber
    -0.07
    ㆍ
    -0.07
    淺
    -0.07
    ','=','
    -0.06
    ảy
    -0.06
    年前
    -0.06
     integrating
    -0.06
    تحميل
    -0.06
    uy
    -0.06
    ⛟
    -0.06
    POSITIVE LOGITS
    的消息
    0.07
    二级
    0.07
    relative
    0.07
    -budget
    0.06
    .resolve
    0.06
    -ag
    0.06
    агент
    0.06
    친
    0.06
    授权
    0.06
    不知不
    0.06
    Act Density 0.002%

    No Known Activations