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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe different ranges or selections of products

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

    range of options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.57
    aarrggbb
    -0.55
     Савезне
    -0.55
     "..\..\
    -0.54
    RenderAtEndOf
    -0.52
     Мексичка
    -0.51
     pinulongan
    -0.50
    IntoConstraints
    -0.48
     Италијани
    -0.47
    windowFixed
    -0.47
    POSITIVE LOGITS
     range
    1.19
    range
    0.92
     RANGE
    0.89
    Range
    0.86
    RANGE
    0.86
     Range
    0.85
     gamme
    0.80
     Sortiment
    0.77
     ranges
    0.77
     assortment
    0.73
    Act Density 0.006%

    No Known Activations