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

    Neuronpedia

    INDEX
    Explanations

    Government and legal matters

    np_max-act · gemini-2.0-flash

    This neuron responds to formal, standardized category nouns—like government bodies (e.g. “Ministry,” “Courts”) or measurement units (“units,” “Newton”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Flush
    -0.07
     TAB
    -0.07
     Discrim
    -0.07
    Роз
    -0.07
     Pizza
    -0.06
     Hardcover
    -0.06
    properties
    -0.06
    ',

↵
    -0.06
     improperly
    -0.06
     persec
    -0.06
    POSITIVE LOGITS
    aho
    0.07
    .Reader
    0.06
    ierre
    0.06
    _locals
    0.06
     नई
    0.06
     '%$
    0.06
    Cisco
    0.06
    cano
    0.06
    exc
    0.06
     сок
    0.06
    Act Density 0.099%

    No Known Activations