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

    Neuronpedia

    INDEX
    Explanations

    language related to patents and inventions

    oai_token-act-pair · gemini-2.0-flash

    Inventions and patents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sh
    -0.47
    DOCTYPE
    -0.43
     š
    -0.42
     perce
    -0.42
    בל
    -0.42
     Ber
    -0.42
    !
    -0.41
     j
    -0.41
     bel
    -0.40
     mas
    -0.40
    POSITIVE LOGITS
    IndentedString
    0.79
     урна
    0.74
     ddelweddau
    0.71
     OFDb
    0.71
     Shakspeare
    0.70
     pinulongan
    0.69
    Mutagenicity
    0.68
     ویکی‌پدی
    0.68
     himſelf
    0.67
     Whigs
    0.66
    Act Density 0.181%

    No Known Activations