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

    Neuronpedia

    INDEX
    Explanations

    variables, placeholders, and syntax components related to programming or scripting languages

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

    dollar, variable, or string delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BrowserModule
    -0.57
    i
    -0.50
     Cori
    -0.45
    eti
    -0.45
    BrowserModule
    -0.45
     viewType
    -0.45
    qtype
    -0.44
    eri
    -0.44
    י
    -0.43
    eci
    -0.43
    POSITIVE LOGITS
    dollar
    0.93
    ://$
    0.88
    ='$
    0.82
    ">$
    0.82
    "$
    0.81
    ="$
    0.81
    ("$
    0.79
    dollars
    0.79
    ('$
    0.79
     ['$
    0.78
    Act Density 0.053%

    No Known Activations