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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Contractors
    -0.07
     Rational
    -0.06
    423
    -0.06
     antagon
    -0.06
    	br
    -0.06
     mirac
    -0.06
     дів
    -0.06
    anim
    -0.06
    "In
    -0.06
    inem
    -0.06
    POSITIVE LOGITS
     debated
    0.07
    romosome
    0.06
     balance
    0.06
     далеко
    0.06
     зависимости
    0.06
    到的
    0.06
     versa
    0.06
    银
    0.06
    :message
    0.06
    Rp
    0.06
    Act Density 0.002%

    No Known Activations