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

    Neuronpedia

    INDEX
    Explanations

    unknown

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens in the “Year of birth unknown” (and similar) category metadata, i.e. on the birth/death year numbers in the category lines.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Buffer
    -0.08
    _stride
    -0.07
     corner
    -0.07
    ่ง
    -0.07
     Btn
    -0.06
    .Pixel
    -0.06
    Adj
    -0.06
    =my
    -0.06
     Corinthians
    -0.06
    ]‏
    -0.06
    POSITIVE LOGITS
     condiciones
    0.06
    autorelease
    0.06
     Yankee
    0.06
     ""),
    0.06
     Barack
    0.06
     entitled
    0.05
    ğmen
    0.05
     Access
    0.05
     <↵
    0.05
    wood
    0.05
    Act Density 0.001%

    No Known Activations