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

    Neuronpedia

    INDEX
    Explanations

    code syntax from different languages including XML and JavaScript

    oai_token-act-pair · gemini-2.0-flash

    references to "FlatList" and various cross patterns

    np_token-act-pair-logits · gpt-4o-mini

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.65
    Datuak
    -0.63
     CreateTagHelper
    -0.60
    Espèce
    -0.57
    umoj
    -0.53
    __(/*!
    -0.50
    AndEndTag
    -0.50
    Diwedd
    -0.49
    KommentareTeilen
    -0.49
    Personendaten
    -0.49
    POSITIVE LOGITS
    帖最后由
    0.71
     cross
    0.66
    cross
    0.66
    PreferredItem
    0.63
    Cross
    0.63
    CROSS
    0.58
     mergeFrom
    0.56
     CROSS
    0.55
     Berry
    0.52
     Cross
    0.51
    Act Density 0.204%

    No Known Activations