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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    This neuron primarily picks up on common English function words (e.g. “the,” “for,” “and,” “he”) rather than content words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (J
    -0.07
     近
    -0.07
    ادا
    -0.07
    clist
    -0.06
    ifty
    -0.06
    Hor
    -0.06
    ández
    -0.06
    dyn
    -0.06
    -speaking
    -0.06
     наступ
    -0.06
    POSITIVE LOGITS
     multiprocessing
    0.07
     Async
    0.07
     contains
    0.06
    	Expect
    0.06
    .seconds
    0.06
     $(".
    0.06
     aquarium
    0.06
     illustrating
    0.06
    髪
    0.06
     ValueEventListener
    0.06
    Act Density 0.171%

    No Known Activations