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

    Neuronpedia

    INDEX
    Explanations

    Property

    np_max-act · gemini-2.0-flash

    The neuron detects the Apple plist DOCTYPE header, in particular the “Property List” DTD declaration (e.g. “Property List –1.0.dtd”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     costumes
    -0.07
     SPELL
    -0.06
     Rush
    -0.06
    _ack
    -0.06
     sesso
    -0.06
     Surveillance
    -0.06
    couz
    -0.06
     Strange
    -0.06
     Lev
    -0.06
    detalle
    -0.06
    POSITIVE LOGITS
    .type
    0.06
     className
    0.06
    /${
    0.06
     getDefault
    0.06
     NoSuchElementException
    0.06
    .placeholder
    0.06
    bilir
    0.06
    (point
    0.06
     getDate
    0.06
     binary
    0.06
    Act Density 0.000%

    No Known Activations