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

    Neuronpedia

    INDEX
    Explanations

    most

    np_max-act · gemini-2.0-flash

    The neuron fires on terms that convey prioritization or importance (e.g. prioritize, most important, urgent).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     事
    -0.06
     حج
    -0.06
     Brewery
    -0.06
     dj
    -0.06
    .questions
    -0.06
     OBS
    -0.06
    <Book
    -0.06
    aft
    -0.06
    요
    -0.06
    사회
    -0.06
    POSITIVE LOGITS
    :invoke
    0.06
    ViewChild
    0.06
     типу
    0.06
    LET
    0.06
    ORIZATION
    0.06
     attachment
    0.06
     wrappers
    0.06
    }{↵
    0.06
    户
    0.06
    -options
    0.06
    Act Density 0.027%

    No Known Activations