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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on code identifiers that end in “Type,” i.e. property or class names suffixed with “Type.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    airo
    -0.07
    <Audio
    -0.07
    ogenerated
    -0.07
     antib
    -0.06
    undra
    -0.06
     Ro
    -0.06
     M
    -0.06
    Sequential
    -0.06
    	My
    -0.06
     fisheries
    -0.06
    POSITIVE LOGITS
     acuerdo
    0.07
     대행
    0.06
     tuyên
    0.06
     svaz
    0.06
     Finder
    0.06
    ,status
    0.06
    ाहक
    0.06
    (commit
    0.06
    -size
    0.06
     пок
    0.06
    Act Density 0.043%

    No Known Activations