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

    Neuronpedia

    INDEX
    Explanations

    orc

    np_max-act · gemini-2.0-flash

    The neuron detects references to exorcism or demonic activity (e.g. “exorc,” “orcism,” “demon,” “possession,” “spirits”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    panse
    -0.07
     fees
    -0.07
     �
    -0.07
    альних
    -0.06
     weather
    -0.06
    AccountId
    -0.06
     shower
    -0.06
    .btnAdd
    -0.06
    >()
    -0.06
     هیچ
    -0.06
    POSITIVE LOGITS
    minated
    0.06
    ری
    0.06
    yme
    0.06
    جار
    0.06
     locksmith
    0.06
    .widgets
    0.06
     revealed
    0.06
    \helpers
    0.06
    rists
    0.06
    Truthy
    0.06
    Act Density 0.004%

    No Known Activations