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

    Neuronpedia

    INDEX
    Explanations

    code structure and programming functions related to boxes and their attributes

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

    The token "box" or related terms

    np_acts-logits-general · gemini-2.0-flash

    DSG boxes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WebDriverWait
    -0.61
    ciutto
    -0.60
    存于互联网档案馆
    -0.60
     disambiguazione
    -0.60
     ujednoznacz
    -0.60
    KommentareTeilen
    -0.59
    ModelAdmin
    -0.56
     adipis
    -0.55
     plantar
    -0.55
     McCl
    -0.54
    POSITIVE LOGITS
     box
    4.14
     Box
    3.74
    box
    3.69
    Box
    3.57
     BOX
    3.30
     boxes
    3.17
    BOX
    3.14
     Boxes
    2.83
    boxes
    2.81
     boxed
    2.64
    Act Density 0.161%

    No Known Activations