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

    Neuronpedia

    INDEX
    Explanations

    Etymology

    np_max-act · gemini-2.0-flash

    This neuron responds to frequent English function words—especially articles and prepositions like “the,” “a,” “in,” “of,” “to,” and “from.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Pop
    -0.06
     videos
    -0.06
    �
    -0.06
    [])
    -0.06
     多
    -0.06
    _planes
    -0.06
    _frequency
    -0.06
     cat
    -0.06
    /maps
    -0.05
    disc
    -0.05
    POSITIVE LOGITS
    .cursor
    0.07
    .Node
    0.07
    ksam
    0.07
     addslashes
    0.07
     kiểu
    0.07
     dataSnapshot
    0.07
     заг
    0.07
     Ukraj
    0.06
     zdravot
    0.06
     докум
    0.06
    Act Density 0.023%

    No Known Activations