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

    Neuronpedia

    INDEX
    Explanations

    London

    np_max-act · gemini-2.0-flash

    This neuron fires when the text mentions the place name “London.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ACE
    -0.09
     Ashe
    -0.07
     erase
    -0.07
     grille
    -0.07
     anime
    -0.07
    Aff
    -0.07
     erg
    -0.07
     Paige
    -0.07
     aff
    -0.07
    appe
    -0.07
    POSITIVE LOGITS
     London
    0.15
    London
    0.13
     Lond
    0.10
     london
    0.08
    ONDON
    0.07
    don
    0.07
     lender
    0.07
    ouncil
    0.07
    .news
    0.07
     �
    0.07
    Act Density 0.006%

    No Known Activations