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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron is triggered by multi‐digit numeric expressions connected by dashes (e.g. “8-2-12,” “4-2-5,” “11–3”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     quil
    -0.08
     min
    -0.07
     YE
    -0.07
    outs
    -0.06
    .calc
    -0.06
    ilda
    -0.06
    xo
    -0.06
    	sig
    -0.06
    mux
    -0.06
     salsa
    -0.06
    POSITIVE LOGITS
    readystatechange
    0.07
    redential
    0.07
    /internal
    0.06
     Minist
    0.06
     authorized
    0.06
    controller
    0.06
     sản
    0.06
     getResource
    0.06
    Title
    0.06
     divisible
    0.06
    Act Density 0.032%

    No Known Activations