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

    Neuronpedia

    INDEX
    Explanations

    words related to legal implications and violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    end of capitalism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Euphrates
    -0.71
     Riks
    -0.63
     Dalai
    -0.63
     quran
    -0.61
     Koran
    -0.60
     Algarve
    -0.60
     Falkland
    -0.59
     IUCN
    -0.59
     Talmud
    -0.59
     pixar
    -0.58
    POSITIVE LOGITS
     America
    0.83
     what
    0.77
     humanity
    0.68
    America
    0.65
     humankind
    0.64
     modern
    0.64
     capitalism
    0.63
     norsk
    0.62
     mankind
    0.62
     the
    0.61
    Act Density 0.480%

    No Known Activations