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

    Neuronpedia

    INDEX
    Explanations

    specific units of measurement and the associated numerical values

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

    units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     souci
    -0.46
     hiszen
    -0.39
     déclar
    -0.37
     råd
    -0.36
     rangkaian
    -0.36
    festa
    -0.35
     défaut
    -0.35
     total
    -0.35
     Total
    -0.34
    وده
    -0.34
    POSITIVE LOGITS
     snippetHide
    0.81
     defaultstate
    0.66
     typelib
    0.64
     للاسماء
    0.61
    BeginContext
    0.60
     NSCoder
    0.60
    sizeCache
    0.59
     propOrder
    0.58
    Diweddarwch
    0.58
    endphp
    0.57
    Act Density 0.220%

    No Known Activations