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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    玉
    -0.06
     projectiles
    -0.06
     JDK
    -0.06
     Cylinder
    -0.06
     Müz
    -0.06
     Natal
    -0.06
     EK
    -0.06
     Normal
    -0.06
     Huntington
    -0.06
     thank
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ,)
    0.06
     serv
    0.06
    เผ
    0.06
     Lesson
    0.06
     convert
    0.06
     اه
    0.06
    ρωση
    0.06
     Сер
    0.06
    encies
    0.06
    Act Density 0.018%

    No Known Activations