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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions related to inequalities and functions

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

    mathematical notation <span>

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.68
    URLException
    -0.68
    Rüyada
    -0.65
    -0.63
    LookAnd
    -0.61
     noDo
    -0.58
    MemoryWarning
    -0.57
     للاسماء
    -0.57
    osť
    -0.57
    AddTagHelper
    -0.56
    POSITIVE LOGITS
     hàng
    0.27
     adev
    0.26
    SPATH
    0.25
     mornings
    0.25
    raquo
    0.23
     draw
    0.23
    ühr
    0.23
    Več
    0.22
    useum
    0.22
     there
    0.22
    Act Density 0.147%

    No Known Activations