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

    Neuronpedia

    INDEX
    Explanations

    references to the act of creating or developing new methods, ideas, or inventions

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

    devise methods, systems, and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     océ
    -0.59
     ingrat
    -0.57
    ########.
    -0.57
     parachoque
    -0.54
    曖昧さ回避
    -0.54
     financière
    -0.52
    llllllll
    -0.52
    majánló
    -0.51
     administratif
    -0.50
     mauva
    -0.50
    POSITIVE LOGITS
     devised
    1.81
     devise
    1.80
     devising
    1.59
    devise
    1.30
     devis
    1.11
     device
    0.93
     designed
    0.78
    device
    0.77
     scheme
    0.77
     Device
    0.75
    Act Density 0.004%

    No Known Activations