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

    Neuronpedia

    INDEX
    Explanations

    patterns related to regular expressions and mathematical notation

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

    regular expression capturing groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.52
    SBATCH
    -0.47
     noDo
    -0.46
    WebServlet
    -0.45
    ///</
    -0.42
     Gier
    -0.40
    ècie
    -0.39
    awtextra
    -0.37
     }{@
    -0.36
    intios
    -0.36
    POSITIVE LOGITS
    csname
    0.57
     <<<<<<<<<<<<<<
    0.54
    Geplaatst
    0.52
    pexpr
    0.51
     CDA
    0.50
    lfloor
    0.49
    cupertino
    0.47
    BeginContext
    0.45
    genetics
    0.44
    tanleria
    0.44
    Act Density 0.182%

    No Known Activations