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

    Neuronpedia

    INDEX
    Explanations

    instances of parenthetical or quoted text that use "hereafter"

    oai_token-act-pair · gemini-2.0-flash

    eafter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.98
    ValueStyle
    -0.96
    contentLoaded
    -0.94
    LookAnd
    -0.94
     الرياضيه
    -0.91
    ंदीखरीदारी
    -0.90
    WebElementEntity
    -0.89
    ContentAsync
    -0.87
    IUrlHelper
    -0.85
     EconPapers
    -0.84
    POSITIVE LOGITS
     called
    0.61
    i
    0.54
    called
    0.54
    L
    0.51
    ter
    0.48
    F
    0.47
    Ter
    0.47
     known
    0.47
    f
    0.46
    лю
    0.46
    Act Density 2.967%

    No Known Activations