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 detects present‐tense “to be” verbs (e.g. “is,” “are”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Markt
    -0.06
    orf
    -0.06
    protein
    -0.06
    _mv
    -0.06
    requ
    -0.06
     Ding
    -0.06
    arcy
    -0.06
     tyto
    -0.06
    (By
    -0.06
     Diese
    -0.06
    POSITIVE LOGITS
    ;"><?
    0.08
     выход
    0.07
    _MATH
    0.06
    CLI
    0.06
     autocomplete
    0.06
    DOI
    0.06
     (),↵
    0.06
     hindsight
    0.06
     /[
    0.06
    一步
    0.06
    Act Density 0.094%

    No Known Activations