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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Deniz
    -0.07
    rav
    -0.06
     invalidate
    -0.06
    ksiyon
    -0.06
     nama
    -0.06
    mens
    -0.06
    .flex
    -0.06
    .GetObject
    -0.06
    状
    -0.06
    .tim
    -0.06
    POSITIVE LOGITS
    ает
    0.07
     پیدا
    0.07
     tăng
    0.07
     국제
    0.06
     pitcher
    0.06
     вед
    0.06
    (cancel
    0.06
    utely
    0.06
     ارزی
    0.06
     tant
    0.06
    Act Density 0.001%

    No Known Activations