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

    Neuronpedia

    INDEX
    Explanations

    family

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of close personal relations—specifically “friends” and “family.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Investigators
    -0.06
     розпов
    -0.06
    ';';
    -0.06
    економ
    -0.06
    istinguished
    -0.06
    degree
    -0.06
    ゆ
    -0.06
    تق
    -0.06
    aturally
    -0.06
     appropriately
    -0.06
    POSITIVE LOGITS
     нужно
    0.07
     harga
    0.07
    essenger
    0.06
     return
    0.06
     она
    0.06
     aku
    0.06
    �재
    0.06
    _DOWN
    0.06
     ona
    0.06
    el
    0.06
    Act Density 0.006%

    No Known Activations