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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    composer
    -0.08
     keto
    -0.08
     candies
    -0.08
     Ln
    -0.08
     ln
    -0.08
    cout
    -0.08
     commercialization
    -0.08
    currency
    -0.08
    ingredients
    -0.08
     OE
    -0.07
    POSITIVE LOGITS
     পুলিশ
    0.16
     ಪೊಲೀಸ್
    0.15
     पुलिस
    0.15
     경찰
    0.14
     policial
    0.14
     Police
    0.13
     പോലീസ്
    0.13
     పోలీస
    0.13
     போலீ
    0.13
     પોલીસ
    0.13
    Act Density 0.137%

    No Known Activations