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

    Neuronpedia

    INDEX
    Explanations

    stock tickers

    np_max-act · gemini-2.0-flash

    This neuron activates on sequences of uppercase letters—specifically stock ticker symbols (e.g., “V”, “MA”, “CRM”, etc.) often shown in parentheses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    满
    -0.07
    ↵     ↵
    -0.06
    (role
    -0.06
     thật
    -0.06
     지
    -0.06
    .ITEM
    -0.06
    .Enter
    -0.06
    写
    -0.06
    BED
    -0.06
    ote
    -0.06
    POSITIVE LOGITS
    止
    0.07
    .assertTrue
    0.07
    되는
    0.07
     avec
    0.07
    。
    0.06
    Party
    0.06
    ساس
    0.06
     Party
    0.06
     DK
    0.06
     Bj
    0.06
    Act Density 0.012%

    No Known Activations