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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting markers within text

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

    description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.52
    Geplaatst
    -0.47
     OFDb
    -0.47
    CROSSTALK
    -0.46
    weightedMode
    -0.46
    تقاوى
    -0.45
    ⓧ
    -0.44
    waitKey
    -0.43
     igjen
    -0.40
    GetAxis
    -0.40
    POSITIVE LOGITS
    description
    0.59
     description
    0.56
    ViewFeatures
    0.54
    MemoryWarning
    0.54
    awtextra
    0.51
    Description
    0.48
    ]")
    0.47
    DESCRIPTION
    0.46
    "]
    0.45
     Purpose
    0.44
    Act Density 0.001%

    No Known Activations