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

    Neuronpedia

    INDEX
    Explanations

    human

    np_max-act · gemini-2.0-flash

    This neuron never fires—it does not detect or respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    imized
    -0.06
    />
    -0.06
    Psy
    -0.06
    izzly
    -0.06
     Butterfly
    -0.06
    _preferences
    -0.06
    eren
    -0.06
     kiện
    -0.06
    ़ो
    -0.06
     महत
    -0.06
    POSITIVE LOGITS
     Establishment
    0.07
    _rem
    0.07
    -Line
    0.07
    _prev
    0.07
     acquired
    0.07
    !',
    0.06
    _REST
    0.06
     provisions
    0.06
     emerges
    0.06
     Proc
    0.06
    Act Density 0.003%

    No Known Activations