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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    This neuron strongly activates on the simple present‐tense copula “is” (and closely related linking verbs) used to state definitions or descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     MF
    -0.07
     Mans
    -0.07
    -core
    -0.06
    pcodes
    -0.06
     alternating
    -0.06
    Core
    -0.06
     registrations
    -0.06
    -language
    -0.06
     strains
    -0.06
     stains
    -0.06
    POSITIVE LOGITS
    σσα
    0.07
     แหล
    0.07
     Да
    0.06
    _basis
    0.06
    .vote
    0.06
     temsil
    0.06
    σμα
    0.06
    @Bean
    0.06
    @register
    0.06
    eft
    0.06
    Act Density 0.077%

    No Known Activations