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

    Neuronpedia

    INDEX
    Explanations

    symbols and operators used in mathematical expressions

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

    mathematical calculations and problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -0.60
    awtextra
    -0.55
     pleaſure
    -0.54
    ConstraintMaker
    -0.52
    ########.
    -0.51
    ValueStyle
    -0.46
    InstrumentedTest
    -0.45
    ReusableCell
    -0.45
    setViewportView
    -0.44
     صفحۀ
    -0.44
    POSITIVE LOGITS
    ViewFeatures
    0.49
    .
    0.47
     We
    0.42
     All
    0.41
     Kitchen
    0.40
     homes
    0.40
     Next
    0.39
    Post
    0.39
     cold
    0.39
     Post
    0.39
    Act Density 0.047%

    No Known Activations