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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating commitment and process descriptions

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

    showing results or figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.66
    GraphicsUnit
    -0.63
     Audiodateien
    -0.60
    UserScript
    -0.58
     betweenstory
    -0.57
     aDecoder
    -0.57
     ویکی‌پدی
    -0.56
    RegressionTest
    -0.56
    Datuak
    -0.55
    onViewCreated
    -0.54
    POSITIVE LOGITS
     showing
    1.20
     Showing
    1.14
     showed
    1.13
    showing
    1.13
     Shows
    1.11
     shown
    1.11
     shows
    1.10
    shows
    1.08
     show
    1.06
    Shows
    1.06
    Act Density 0.117%

    No Known Activations