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

    Neuronpedia

    INDEX
    Explanations

    aur

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Blackjack
    -0.07
    'al
    -0.07
     blackjack
    -0.07
    ndo
    -0.07
     Bronx
    -0.06
     Blink
    -0.06
     ліка
    -0.06
    	stack
    -0.06
    '))->
    -0.06
     Elsa
    -0.06
    POSITIVE LOGITS
     aur
    0.09
    our
    0.07
    vironment
    0.07
     Aur
    0.07
    ον
    0.07
    程
    0.07
     Laur
    0.06
    ParameterValue
    0.06
     Maurice
    0.06
    aur
    0.06
    Act Density 0.010%

    No Known Activations