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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to tensor manipulation in programming

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

    array dimensions and reshaping

    np_acts-logits-general · gemini-2.0-flash

    tensor shape manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.35
     setEmail
    -0.34
     приш
    -0.29
     pla
    -0.28
    Kanpo
    -0.27
     %.
    -0.26
     tull
    -0.26
     leg
    -0.26
     пришел
    -0.26
     pen
    -0.26
    POSITIVE LOGITS
    DockStyle
    0.71
    setVerticalGroup
    0.68
    AddTagHelper
    0.65
    InputBorder
    0.64
    AnchorStyles
    0.62
     lenker
    0.60
     المعيارى
    0.60
    makeConstraints
    0.59
    webElementXpaths
    0.59
    AutoresizingMask
    0.59
    Act Density 0.244%

    No Known Activations