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

    Neuronpedia

    INDEX
    Explanations

    Gypsies and Roma

    np_max-act · gemini-2.0-flash

    historical references and discussions surrounding the Holocaust and its associated narratives.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on mentions of the Romani/“gypsy” group (i.e. tokens composing “gypsies” or “Romani”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    neutral
    -0.07
    Seed
    -0.07
     murderous
    -0.06
    Cake
    -0.06
    )";↵
    -0.06
    Bone
    -0.06
    Im
    -0.06
     nors
    -0.06
     Mayweather
    -0.06
     nen
    -0.06
    POSITIVE LOGITS
     عمومی
    0.07
    ِّ
    0.06
     payments
    0.06
     Pandora
    0.06
     رضا
    0.06
     generalize
    0.06
    yps
    0.06
     Unique
    0.06
    .hm
    0.06
    lias
    0.06
    Act Density 0.001%

    No Known Activations