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

    Neuronpedia

    INDEX
    Explanations

    powered

    np_max-act · gemini-2.0-flash

    This neuron activates on the substring “powered,” most notably in hyphenated adjectives like “AI-powered.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     fabrics
    -0.09
    _tags
    -0.07
     newArray
    -0.07
    	cell
    -0.07
     scope
    -0.06
     HLS
    -0.06
     disparate
    -0.06
     range
    -0.06
     Worker
    -0.06
     rencontr
    -0.06
    POSITIVE LOGITS
     powered
    0.10
    Powered
    0.08
     Powered
    0.07
    ?s
    0.07
    -powered
    0.07
     Fang
    0.07
     Charleston
    0.07
     overpower
    0.07
    탄
    0.06
    webkit
    0.06
    Act Density 0.007%

    No Known Activations