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

    Neuronpedia

    INDEX
    Explanations

    scams

    np_max-act · gemini-2.0-flash

    The neuron responds to proper names and titles—i.e. named entities such as people’s names, job titles, or organization names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _address
    -0.06
     Coffee
    -0.06
    season
    -0.06
     ],
↵
    -0.06
     executive
    -0.06
    front
    -0.06
    ircraft
    -0.06
     مز
    -0.06
     Leia
    -0.05
     ya
    -0.05
    POSITIVE LOGITS
    ermo
    0.07
     __________________
    0.07
    (anchor
    0.07
    _USAGE
    0.07
    орі
    0.06
    %'
    0.06
    	ans
    0.06
     hik
    0.06
     Дон
    0.06
    -D
    0.06
    Act Density 0.087%

    No Known Activations