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

    Neuronpedia

    INDEX
    Explanations

    API

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “API” (and related API mentions) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    แห
    -0.07
    .include
    -0.07
     enclosed
    -0.07
     Grape
    -0.06
    erchant
    -0.06
     mercenaries
    -0.06
    allon
    -0.06
    헤
    -0.06
     engr
    -0.06
     Harding
    -0.06
    POSITIVE LOGITS
    <>↵
    0.07
    0.07
    افه
    0.06
    	for
    0.06
     zusammen
    0.06
     JOHN
    0.06
     الأد
    0.06
     commenting
    0.06
     expecting
    0.06
    _API
    0.06
    Act Density 0.006%

    No Known Activations