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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =row
    -0.06
     сад
    -0.06
    	world
    -0.06
     ciz
    -0.06
     Bye
    -0.06
     videog
    -0.06
     Ocean
    -0.06
     patrol
    -0.06
    ,input
    -0.06
     виду
    -0.05
    POSITIVE LOGITS
     informace
    0.08
    حداث
    0.07
     exported
    0.07
     Matthew
    0.07
     Mars
    0.06
     перепис
    0.06
    OURCES
    0.06
    meal
    0.06
     milionů
    0.06
     빛
    0.06
    Act Density 0.028%

    No Known Activations