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

    Neuronpedia

    INDEX
    Explanations

    numeric values in various contexts

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

    shell arguments and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.71
     <<<<<<<<<<<<<<
    -0.53
    styleType
    -0.49
     OMITBAD
    -0.44
    XtraReports
    -0.43
    mobileqq
    -0.42
    TagMode
    -0.42
    ronpa
    -0.41
    OrEqual
    -0.39
    memberof
    -0.36
    POSITIVE LOGITS
     $#
    0.67
     ExecuteAsync
    0.65
     onPostExecute
    0.53
     "$@"
    0.52
     StatelessWidget
    0.48
    ARGV
    0.47
    存于互联网档案馆
    0.47
    CreateModel
    0.45
    StartTag
    0.43
    SourceChecksum
    0.43
    Act Density 0.015%

    No Known Activations