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

    Neuronpedia

    INDEX
    Explanations

    religion

    np_max-act · gemini-2.0-flash

    This neuron fires on words and phrases explicitly naming or referring to religion and belief (e.g. “religion,” “religious,” “faith,” “God”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cmap
    -0.07
    ступ
    -0.07
     beds
    -0.07
    (cancel
    -0.07
    rstrip
    -0.06
    кул
    -0.06
     [[]
    -0.06
     จาก
    -0.06
     processed
    -0.06
     talk
    -0.06
    POSITIVE LOGITS
     WK
    0.06
    Scotland
    0.06
     ию
    0.06
    šení
    0.06
     arttır
    0.06
     Semiconductor
    0.06
    ?p
    0.06
     tisí
    0.06
     museum
    0.06
     Sr
    0.06
    Act Density 0.025%

    No Known Activations