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

    Neuronpedia

    INDEX
    Explanations

    morality

    np_max-act · gemini-2.0-flash

    This neuron activates on philosophical and ethics‐related terminology, e.g. words about morality, ethics, ontology, philosophy.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    xpath
    -0.06
    Salt
    -0.06
    态
    -0.06
    FOR
    -0.06
    До
    -0.06
    AccessType
    -0.06
     straight
    -0.06
    	map
    -0.06
    gross
    -0.06
    edula
    -0.06
    POSITIVE LOGITS
    rowned
    0.06
    y
    0.06
    yb
    0.06
    _lcd
    0.06
     musique
    0.06
     incredible
    0.06
    :@"%@",
    0.06
     Fifth
    0.06
    <|begin_of_text|>
    0.06
    /mp
    0.06
    Act Density 0.041%

    No Known Activations