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

    Neuronpedia

    INDEX
    Explanations

    aware

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	where
    -0.07
     uçak
    -0.07
     taboo
    -0.06
     MEMBER
    -0.06
    析
    -0.06
    EVER
    -0.06
     Equation
    -0.06
     negot
    -0.06
     WHY
    -0.06
    明天
    -0.06
    POSITIVE LOGITS
    олод
    0.08
    江北
    0.08
    (login
    0.08
    的真实性
    0.07
    旁边
    0.07
    (_
    0.07
     المختلفة
    0.07
     surround
    0.07
    homes
    0.07
     الفلسطين
    0.07
    Act Density 0.225%

    No Known Activations