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

    Neuronpedia

    INDEX
    Explanations

    requests for increased privacy and security regarding electronic devices

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

    preceding hypothetical scenarios

    np_acts-logits-general · gemini-2.0-flash

    optional automatic functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.70
    ellido
    -0.60
    BeginInit
    -0.60
     ieri
    -0.58
    ElementException
    -0.57
    fony
    -0.57
     senaste
    -0.56
     habituellement
    -0.55
    RenderAtEndOf
    -0.54
    šinou
    -0.54
    POSITIVE LOGITS
     maybe
    1.09
     would
    1.01
    maybe
    0.95
     perhaps
    0.94
    would
    0.88
     Would
    0.87
     Maybe
    0.86
    perhaps
    0.83
    Maybe
    0.80
     Wouldn
    0.79
    Act Density 0.781%

    No Known Activations