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

    Neuronpedia

    INDEX
    Explanations

    refugee

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “refugee” (and its plural form) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     SCRIPT
    -0.07
     tomato
    -0.07
     brit
    -0.07
     Python
    -0.07
     earned
    -0.07
     아이콘
    -0.06
     Mater
    -0.06
     Wear
    -0.06
     Brit
    -0.06
     jylland
    -0.06
    POSITIVE LOGITS
     refugee
    0.11
     refugees
    0.11
     Refugee
    0.10
     Refuge
    0.08
    neo
    0.08
     refuge
    0.08
     prejudice
    0.07
     congestion
    0.07
    िए
    0.07
    .RequestBody
    0.07
    Act Density 0.002%

    No Known Activations