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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases that indicate inclusion or location—e.g. “in,” “included,” “incorporated.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Temple
    -0.08
     standpoint
    -0.07
     Township
    -0.06
     Sanctuary
    -0.06
    彩票
    -0.06
     MetroFramework
    -0.06
    尖
    -0.06
     Desktop
    -0.06
     conquered
    -0.06
     Trap
    -0.06
    POSITIVE LOGITS
     kesin
    0.09
     неболь
    0.08
     included
    0.08
     incred
    0.08
     inform
    0.07
     количе
    0.07
     arrang
    0.07
     reck
    0.07
     enlight
    0.07
     includes
    0.07
    Act Density 0.019%

    No Known Activations