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

    Neuronpedia

    INDEX
    Explanations

    libertarian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     மட்ட
    -0.09
     മാത്ര
    -0.08
     crawling
    -0.08
     fath
    -0.08
    ହ
    -0.08
     indoors
    -0.08
     आइ
    -0.08
     Hersteller
    -0.08
     sèlman
    -0.08
    厂家
    -0.08
    POSITIVE LOGITS
     libert
    0.12
     liberties
    0.09
     minded
    0.09
    -minded
    0.08
     liberal
    0.08
    agan
    0.08
     либ
    0.08
    	exit
    0.08
     Judaism
    0.08
     деньги
    0.08
    Act Density 0.008%

    No Known Activations