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

    Neuronpedia

    INDEX
    Explanations

    mention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    她的
    -0.08
    _red
    -0.07
     полов
    -0.07
    jourd
    -0.07
     læ
    -0.07
    ยน
    -0.06
    ayı
    -0.06
    ιλο
    -0.06
    gallery
    -0.06
    ощи
    -0.06
    POSITIVE LOGITS
     UNIX
    0.07
    ;&
    0.07
    (origin
    0.07
     except
    0.06
    枚
    0.06
     wordpress
    0.06
    출장안마
    0.06
    ialias
    0.06
     Pharm
    0.06
     Clair
    0.06
    Act Density 0.000%

    No Known Activations