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

    Neuronpedia

    INDEX
    Explanations

    R

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getX
    -0.07
    ع
    -0.07
    ходить
    -0.06
    다가
    -0.06
     Enlightenment
    -0.06
    통신
    -0.06
    анси
    -0.06
    getc
    -0.06
    Њ
    -0.06
    스크
    -0.06
    POSITIVE LOGITS
     compression
    0.07
    [axis
    0.06
    _world
    0.06
    uccess
    0.06
     Log
    0.06
    send
    0.06
     stirred
    0.06
     collector
    0.06
    addresses
    0.06
    rub
    0.06
    Act Density 0.001%

    No Known Activations