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

    Neuronpedia

    INDEX
    Explanations

    formal languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     자동
    -0.07
     wyst
    -0.07
    GPL
    -0.07
    નની
    -0.07
     worms
    -0.07
     늘
    -0.07
    自动
    -0.07
     desks
    -0.07
     автоматически
    -0.07
    骗局
    -0.07
    POSITIVE LOGITS
    umos
    0.09
    имой
    0.08
    itrate
    0.08
     Casc
    0.08
    회원
    0.08
     overweight
    0.07
    _session
    0.07
     Zach
    0.07
    _prop
    0.07
     باقي
    0.07
    Act Density 0.000%

    No Known Activations