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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     birbir
    -0.06
    成人
    -0.06
     глуб
    -0.06
    วด
    -0.06
     ChatColor
    -0.06
     Sector
    -0.06
     دفاع
    -0.06
     Vậy
    -0.06
     تفاوت
    -0.06
     biệt
    -0.06
    POSITIVE LOGITS
     families
    0.07
     unpopular
    0.07
     revered
    0.07
     Winds
    0.07
    estimated
    0.07
    æk
    0.06
     Set
    0.06
     Modifications
    0.06
    dbl
    0.06
     anzeigen
    0.06
    Act Density 0.068%

    No Known Activations