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

    Neuronpedia

    INDEX
    Explanations

    Biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lesson
    -0.07
     حول
    -0.07
    Resource
    -0.07
     ];↵↵
    -0.07
     deferred
    -0.07
    Eric
    -0.07
    إخ
    -0.06
    墼
    -0.06
    &↵
    -0.06
    .token
    -0.06
    POSITIVE LOGITS
     upp
    0.07
     Finals
    0.07
     правитель
    0.07
     בלי
    0.07
    _miss
    0.07
    ಪ
    0.07
    oğlu
    0.07
     unable
    0.07
    kür
    0.06
     sigu
    0.06
    Act Density 0.016%

    No Known Activations