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

    Neuronpedia

    INDEX
    Explanations

    C++ code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    імі
    -0.07
    ."_
    -0.06
    ädchen
    -0.06
    Markdown
    -0.06
    	h
    -0.06
     Archae
    -0.06
    ticker
    -0.06
    antanamo
    -0.06
     هاي
    -0.06
    -fast
    -0.06
    POSITIVE LOGITS
     bát
    0.07
    withdraw
    0.07
     폐
    0.06
     Autor
    0.06
     accompanying
    0.06
     stocks
    0.06
    康
    0.06
     reconstructed
    0.06
     eBay
    0.06
    (enc
    0.06
    Act Density 0.178%

    No Known Activations