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

    Neuronpedia

    INDEX
    Explanations

    why understand

    np_max-act · gemini-2.0-flash

    The neuron lights up on first‐person “I … why” constructions that introduce an explanation or expression of understanding (e.g. “I get why…,” “I understand why…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    abcdefghijklmnop
    -0.06
    _msgs
    -0.06
    續
    -0.06
    (require
    -0.06
    톤
    -0.06
    .genre
    -0.06
     scattering
    -0.06
     영국
    -0.06
     QUEUE
    -0.06
     Powered
    -0.06
    POSITIVE LOGITS
    ژه
    0.07
    repeat
    0.07
    买
    0.07
    Par
    0.06
    านคร
    0.06
     pnl
    0.06
     UIT
    0.06
    CHED
    0.06
     Represent
    0.06
    二十
    0.06
    Act Density 0.022%

    No Known Activations