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

    Neuronpedia

    INDEX
    Explanations

    references to character encoding formats, specifically UTF-8

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

    utf-8 encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorTagHelper
    -0.54
    sizeCache
    -0.53
    quelize
    -0.52
    queryInterface
    -0.51
    testify
    -0.51
    gbaar
    -0.51
    verifyException
    -0.51
     Perſ
    -0.51
    GHIJKLM
    -0.50
    ListItemIcon
    -0.49
    POSITIVE LOGITS
    UTF
    0.83
    utf
    0.76
     utf
    0.64
     UTF
    0.63
    Utf
    0.45
    <thead>
    0.44
     CanadaChoose
    0.43
     للاسماء
    0.41
    Autoritní
    0.39
    Language
    0.37
    Act Density 0.002%

    No Known Activations