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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ارزیابی
    -0.06
    深
    -0.06
    nou
    -0.06
     увид
    -0.06
    \u
    -0.06
    Hay
    -0.06
    'R
    -0.06
    nov
    -0.06
     siguientes
    -0.06
     ew
    -0.06
    POSITIVE LOGITS
     DAY
    0.07
     useEffect
    0.07
    /course
    0.07
    doesn
    0.07
     знаход
    0.07
     chiếc
    0.07
    ornment
    0.07
     of
    0.06
    。。↵↵
    0.06
    ัฒ
    0.06
    Act Density 0.015%

    No Known Activations