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

    Neuronpedia

    INDEX
    Explanations

    like or minded

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Origins
    -0.07
    films
    -0.07
     intermediary
    -0.07
     règle
    -0.07
     rooted
    -0.06
    visible
    -0.06
    utoff
    -0.06
     Window
    -0.06
    Ѩ
    -0.06
    eyond
    -0.06
    POSITIVE LOGITS
    antiago
    0.08
    سك
    0.08
    اتهم
    0.07
    roperties
    0.07
    ampilkan
    0.07
    пуска
    0.07
     Programm
    0.07
    컷
    0.07
     junto
    0.07
     wallpapers
    0.07
    Act Density 0.008%

    No Known Activations