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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Factor
    -0.07
    198
    -0.06
     ты
    -0.06
     Temper
    -0.06
     primes
    -0.06
    _NUM
    -0.06
     Food
    -0.06
     sce
    -0.06
    functional
    -0.06
    echn
    -0.06
    POSITIVE LOGITS
     sudden
    0.07
    >{{$
    0.06
     příspěv
    0.06
     зах
    0.06
    /header
    0.06
    CDATA
    0.06
    atform
    0.06
    uben
    0.06
     currentPosition
    0.06
    	e
    0.06
    Act Density 0.182%

    No Known Activations