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
     memiliki
    -0.07
     Erl
    -0.07
     Prod
    -0.06
    诏
    -0.06
     select
    -0.06
     NASA
    -0.06
     Students
    -0.06
    -that
    -0.06
    ключения
    -0.06
    Lesson
    -0.06
    POSITIVE LOGITS
     sinus
    0.08
    .pan
    0.07
    מנע
    0.07
    从来没
    0.07
    מיני
    0.06
    ℱ
    0.06
    腻
    0.06
    ➮
    0.06
    .LinkedList
    0.06
     замеча
    0.06
    Act Density 0.093%

    No Known Activations