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

    Neuronpedia

    INDEX
    Explanations

    Royalty

    np_max-act · gemini-2.0-flash

    This neuron activates on royal or honorific titles (e.g., “His Majesty,” “Highness”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     libro
    -0.07
     emitter
    -0.06
     incontro
    -0.06
     cafe
    -0.06
     borrower
    -0.06
     crappy
    -0.06
    |array
    -0.06
    \uff
    -0.06
     реб
    -0.06
    いる
    -0.06
    POSITIVE LOGITS
     massa
    0.07
    PEED
    0.07
     dryer
    0.07
     Valley
    0.07
    _AFTER
    0.07
    status
    0.07
    огод
    0.07
    Highest
    0.07
    .Summary
    0.06
    _ORIENTATION
    0.06
    Act Density 0.001%

    No Known Activations