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

    Neuronpedia

    INDEX
    Explanations

    >>

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the C++ stream‐extraction operator “>>,” i.e. input via `cin >>`.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    에서의
    -0.07
    ای
    -0.07
     مالی
    -0.07
    	int
    -0.06
     Premiership
    -0.06
    	sb
    -0.06
    átis
    -0.06
    잡담
    -0.06
    CW
    -0.06
    火
    -0.06
    POSITIVE LOGITS
     announcements
    0.07
     DDR
    0.07
     seamlessly
    0.06
    งม
    0.06
     subscribe
    0.06
    eryl
    0.06
    ?p
    0.06
     too
    0.06
    resas
    0.06
    _os
    0.06
    Act Density 0.001%

    No Known Activations