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

    Neuronpedia

    INDEX
    Explanations

    Bing

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on the token “Bing” (and variants), i.e. mentions of the Bing search engine.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Rep
    -0.07
    bohydr
    -0.07
     chili
    -0.06
    сок
    -0.06
    _SELECTION
    -0.06
     quite
    -0.06
    .Comp
    -0.06
     حر
    -0.06
    .char
    -0.06
     join
    -0.06
    POSITIVE LOGITS
     Bing
    0.08
    ηση
    0.07
    		
↵
↵
    0.07
     '}↵
    0.07
     :=
    0.07
    σεις
    0.07
    redirect
    0.07
    panse
    0.06
     Wilmington
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations