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

    Neuronpedia

    INDEX
    Explanations

    Articles

    np_max-act · gemini-2.0-flash

    The neuron activates on the phrase “for the” as used to introduce an ordinal occurrence (e.g. “won the World Cup for the fourth time”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _word
    -0.07
    graphs
    -0.07
    example
    -0.07
    闻
    -0.07
     گرفته
    -0.07
    _urls
    -0.06
    Override
    -0.06
     doses
    -0.06
    _legal
    -0.06
     бак
    -0.06
    POSITIVE LOGITS
    .`);↵
    0.06
     حذ
    0.06
     Erica
    0.06
    ensagem
    0.06
    	export
    0.06
    )
↵
↵
↵
    0.06
     Augusta
    0.06
    along
    0.06
    рь
    0.06
    iêu
    0.06
    Act Density 0.019%

    No Known Activations