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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ValueGenerationStrategy
    -0.07
     setSearch
    -0.06
     kicking
    -0.06
     Blackjack
    -0.06
     affordable
    -0.06
    ,private
    -0.06
    ople
    -0.06
     Jul
    -0.06
     복
    -0.06
     년도별
    -0.06
    POSITIVE LOGITS
    صه
    0.07
     reference
    0.07
    дов
    0.06
     Fib
    0.06
     uso
    0.06
     Reference
    0.06
     именно
    0.06
    }
    0.06
    Pix
    0.06
    结束
    0.06
    Act Density 0.024%

    No Known Activations