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

    Neuronpedia

    INDEX
    Explanations

    ive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     borrowing
    -0.07
     strategically
    -0.07
    .ON
    -0.06
    意味
    -0.06
    -urlencoded
    -0.06
    -oriented
    -0.06
    Train
    -0.06
     Filipino
    -0.06
    uchs
    -0.06
     піз
    -0.06
    POSITIVE LOGITS
    335
    0.07
    );;↵
    0.07
    ‌شده
    0.06
     Solution
    0.06
     stuffed
    0.06
     пов
    0.06
     Discounts
    0.06
    WindowTitle
    0.06
     Worldwide
    0.06
    09
    0.06
    Act Density 0.002%

    No Known Activations