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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to computations or programming contexts

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

    Numbers and symbols

    np_acts-logits-general · gemini-2.0-flash

    phone numbers and legal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.78
    ########.
    -0.71
     Paglinawan
    -0.70
    unhofer
    -0.63
     ddelweddau
    -0.63
     gynhyrchwyd
    -0.62
    phite
    -0.60
     kak
    -0.59
     Italijani
    -0.58
    RTEE
    -0.57
    POSITIVE LOGITS
    MessageOf
    0.66
     titolata
    0.64
    UnitTesting
    0.63
     Banten
    0.61
     trekken
    0.61
     défendre
    0.60
     efficacité
    0.60
     tfsi
    0.59
     Pokies
    0.58
    Strauss
    0.58
    Act Density 0.575%

    No Known Activations