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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and symbols related to calculus and probability

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

    partial derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aClass
    -0.39
     ब्रेकडाउन
    -0.37
     classes
    -0.34
     passage
    -0.34
     klass
    -0.32
     files
    -0.32
     stuff
    -0.31
    toMatchSnapshot
    -0.31
     flash
    -0.31
     spell
    -0.30
    POSITIVE LOGITS
     المعيارى
    0.65
    Diweddarwch
    0.57
    ValueStyle
    0.56
     Wikimedijinoj
    0.56
    AutoresizingMask
    0.55
    RuleContext
    0.53
    SequentialGroup
    0.52
    tvguidetime
    0.49
    OGND
    0.48
    ItemBackground
    0.48
    Act Density 0.388%

    No Known Activations