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

    Neuronpedia

    INDEX
    Explanations

    phrases related to consequences and responsibilities in various contexts

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

    computational resourcesdanger unless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.74
    ItemBackground
    -0.69
     betweenstory
    -0.58
     بيها
    -0.55
     disambiguazione
    -0.54
    cloudfront
    -0.51
    )');
    -0.49
    LayoutStyle
    -0.48
    %)$
    -0.47
     זאת
    -0.47
    POSITIVE LOGITS
    outSlope
    0.31
     AssemblyCompany
    0.31
     externi
    0.30
    MLLoader
    0.29
    новниш
    0.28
    ષ
    0.28
     failure
    0.28
     innocent
    0.27
     blank
    0.27
     enkelt
    0.27
    Act Density 0.046%

    No Known Activations