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

    Neuronpedia

    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash

    This neuron fires on the word “both,” especially when it introduces a paired descriptive phrase (as in “both inconspicuous and asymptomatic”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     διά
    -0.07
     �
    -0.07
    eday
    -0.07
     грав
    -0.07
     配
    -0.07
    onestly
    -0.07
    uhl
    -0.07
     Bowman
    -0.06
    овор
    -0.06
     Goth
    -0.06
    POSITIVE LOGITS
    .scrollTo
    0.08
     removing
    0.07
     both
    0.06
     hurricanes
    0.06
    okable
    0.06
    ANDOM
    0.06
    0.06
     padding
    0.06
    nr
    0.06
    Either
    0.06
    Act Density 0.112%

    No Known Activations