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

    Neuronpedia

    INDEX
    Explanations

    variations of the prefix "ex" indicating some form of externalization or removal

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

    starting with "Ex" or "ex"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Ex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.82
    TagHelper
    -0.65
    IntoConstraints
    -0.61
    下载附件
    -0.58
    rrggbb
    -0.58
    licenses
    -0.57
    WebElementEntity
    -0.56
    \{\\
    -0.56
     EconPapers
    -0.54
    ateness
    -0.54
    POSITIVE LOGITS
     Ex
    0.93
    ex
    0.92
     ex
    0.92
    Ex
    0.92
     EX
    0.89
    EX
    0.68
     exc
    0.60
     exp
    0.56
    exp
    0.55
     EXT
    0.53
    Act Density 0.091%

    No Known Activations