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

    Neuronpedia

    INDEX
    Explanations

    strings of code or mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    Math/Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -0.60
     whereof
    -0.60
    -------------</
    -0.59
     taxation
    -0.58
     myſelf
    -0.57
     gallows
    -0.57
     adjournment
    -0.56
     photolibrary
    -0.56
     lugs
    -0.54
    ocarditis
    -0.54
    POSITIVE LOGITS
    AddTagHelper
    0.74
     EconPapers
    0.62
    ftagPool
    0.59
    setHorizontal
    0.52
    انجليز
    0.50
    expandindo
    0.50
    限定
    0.47
     Vikipedi
    0.46
    NameInMap
    0.46
    Autoritní
    0.45
    Act Density 6.342%

    No Known Activations