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

    Neuronpedia

    INDEX
    Explanations

    population census

    np_max-act · gemini-2.0-flash

    The neuron fires on words naming settlement types—e.g. “village,” “town,” or “city.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    solete
    -0.07
    夜
    -0.07
    -0.07
    :>
    -0.06
     :)
    -0.06
     Saturdays
    -0.06
     comprise
    -0.06
    etas
    -0.06
     implements
    -0.06
     `\
    -0.06
    POSITIVE LOGITS
     priesthood
    0.07
    (newState
    0.06
    문제
    0.06
     تش
    0.06
    .Export
    0.06
     GRA
    0.06
     ridicule
    0.06
     �
    0.06
    _cliente
    0.06
    _CM
    0.06
    Act Density 0.002%

    No Known Activations