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

    Neuronpedia

    INDEX
    Explanations

    present

    np_max-act · gemini-2.0-flash

    The neuron fires on the word “present” as used in patent‐style phrases (e.g. “present invention”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _assert
    -0.07
    moved
    -0.07
    .exist
    -0.07
    marked
    -0.07
    .webdriver
    -0.07
     parachute
    -0.07
     graphene
    -0.06
    library
    -0.06
    .pic
    -0.06
     establishing
    -0.06
    POSITIVE LOGITS
    ?>">↵
    0.07
    placeholder
    0.06
     بیماری
    0.06
     FLOAT
    0.06
    Margin
    0.06
     Marg
    0.06
     각각
    0.06
     cep
    0.06
    }"↵↵
    0.06
    ..."↵↵
    0.06
    Act Density 0.003%

    No Known Activations