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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash

    This neuron activates on personal names (capitalized proper names of individuals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Brut
    -0.07
    からの
    -0.07
    -choice
    -0.06
    呀
    -0.06
    请选择
    -0.06
    ่าน
    -0.06
    ,double
    -0.06
     самост
    -0.06
    �
    -0.06
    уже
    -0.06
    POSITIVE LOGITS
    Si
    0.07
    vers
    0.06
     JACK
    0.06
     strategist
    0.06
    –
    0.06
    fred
    0.06
     göster
    0.06
     uniqu
    0.06
     فرودگاه
    0.06
     key
    0.06
    Act Density 0.072%

    No Known Activations