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

    Neuronpedia

    INDEX
    Explanations

    references to regular expressions and their syntax

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

    RegExp and Dixon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    -0.56
    0
    -0.53
    1
    -0.52
    5
    -0.52
    s
    -0.50
    3
    -0.50
    (
    -0.48
    _
    -0.48
    is
    -0.47
    Du
    -0.47
    POSITIVE LOGITS
     RegExp
    1.45
    RegExp
    1.07
    regexp
    0.94
     Numerade
    0.82
     regexp
    0.81
    aarrggbb
    0.75
    Regexp
    0.73
     desmotivaciones
    0.71
    ніципалі
    0.68
     transfieras
    0.67
    Act Density 0.002%

    No Known Activations