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

    Neuronpedia

    INDEX
    Explanations

    closing parentheses and specific syntactical markers in programming

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

    hyphens and closing brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelper
    -0.54
    SEGUIR
    -0.43
    XmlAccessorType
    -0.43
     ollut
    -0.36
     eût
    -0.36
    LEGGI
    -0.35
    NameInMap
    -0.34
    Ārējās
    -0.34
     CGPoint
    -0.34
     BrowserModule
    -0.34
    POSITIVE LOGITS
    --)
    2.92
    --){
    2.47
    --)
    2.44
    --]
    1.39
    –)
    1.00
    --,
    0.99
     -)
    0.94
     (--
    0.89
    --"
    0.88
    -)
    0.87
    Act Density 0.001%

    No Known Activations