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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the indefinite article “a.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Draw
    -0.07
     MEM
    -0.07
    opoly
    -0.06
    公園
    -0.06
    _Mod
    -0.06
    (param
    -0.06
     System
    -0.06
     Sites
    -0.06
    hes
    -0.06
     frail
    -0.06
    POSITIVE LOGITS
     dah
    0.07
     Pleasant
    0.06
     pleas
    0.06
     ''
    0.06
    言い
    0.06
    [jj
    0.06
    Counts
    0.06
    ograph
    0.06
     RequestMethod
    0.06
     طب
    0.06
    Act Density 0.029%

    No Known Activations