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

    Neuronpedia

    INDEX
    Explanations

    Francisco

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “San Francisco” (including variations like “San Francisco Bay Area”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -opt
    -0.08
    (em
    -0.07
    �
    -0.06
     Jac
    -0.06
    (ans
    -0.06
     Lew
    -0.06
    _led
    -0.06
     Lena
    -0.06
    357
    -0.06
    _again
    -0.06
    POSITIVE LOGITS
     Francisco
    0.11
     SF
    0.08
    τσι
    0.07
    ां
    0.07
     usando
    0.07
     dó
    0.07
    AYOUT
    0.07
     Đảng
    0.07
    로부터
    0.07
    われる
    0.07
    Act Density 0.006%

    No Known Activations