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 is tuned to pick up explicit references to God or divine action (e.g., “God,” “Lord,” “His,” “pray,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     HttpContext
    -0.07
     달
    -0.07
     DA
    -0.07
     �
    -0.07
    手に
    -0.06
    ******/
    -0.06
     abyss
    -0.06
    .Strings
    -0.06
    鸟
    -0.06
     ingen
    -0.06
    POSITIVE LOGITS
    活
    0.07
    adder
    0.06
    血
    0.06
    rors
    0.06
    زاده
    0.06
    ?,?,?,?,
    0.06
     breakthrough
    0.06
    제
    0.06
    Liv
    0.06
    _feat
    0.06
    Act Density 0.020%

    No Known Activations