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

    Neuronpedia

    INDEX
    Explanations

    Reader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NFTs
    -0.09
     cryptocurrencies
    -0.08
     ATP
    -0.08
    ależ
    -0.08
     porn
    -0.08
     aviation
    -0.08
     criminal
    -0.08
     unmet
    -0.08
     retail
    -0.08
     normative
    -0.07
    POSITIVE LOGITS
    .Buffered
    0.11
     Buffered
    0.11
    Buffered
    0.11
    .Reader
    0.10
    .readline
    0.10
    	Buffered
    0.10
    	writer
    0.09
    .readlines
    0.09
     readline
    0.09
     buffered
    0.09
    Act Density 0.002%

    No Known Activations