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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash

    This neuron detects the phrasing around census population counts (e.g. “at the 2010 census”) in demographic sections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Integral
    -0.07
    -binary
    -0.06
    Ford
    -0.06
    циональ
    -0.06
    ठ
    -0.06
     affluent
    -0.06
    /system
    -0.06
    �
    -0.06
     Binary
    -0.06
     Corner
    -0.06
    POSITIVE LOGITS
    chen
    0.07
     맞
    0.06
     hiệu
    0.06
     ότι
    0.06
     ตอน
    0.06
    услов
    0.06
     wann
    0.06
     ấy
    0.06
     �
    0.06
     JSBracketAccess
    0.06
    Act Density 0.002%

    No Known Activations