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

    Neuronpedia

    INDEX
    Explanations

    God

    np_max-act · gemini-2.0-flash

    The neuron primarily detects references to God or other divine/higher-power concepts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    لمات
    -0.07
     Colin
    -0.07
    चन
    -0.07
     말이
    -0.07
    .include
    -0.06
     أبي
    -0.06
    .fixed
    -0.06
    άνω
    -0.06
    Mount
    -0.06
     también
    -0.06
    POSITIVE LOGITS
     Christian
    0.07
     dx
    0.06
     Львів
    0.06
     propensity
    0.06
     Dem
    0.06
    -show
    0.06
     customary
    0.06
     Boolean
    0.06
    CharCode
    0.06
    _ot
    0.06
    Act Density 0.043%

    No Known Activations