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

    Neuronpedia

    INDEX
    Explanations

    Grammatical sentences

    np_max-act · gemini-2.0-flash

    This neuron activates on generic factual statement openings—specifically on phrases of the form “The X is Y” (e.g. “The city is home to…,” “The largest of these is…,” “The city is an important center…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _CONV
    -0.07
    PARSE
    -0.07
    lagen
    -0.06
     pais
    -0.06
    -bo
    -0.06
    AME
    -0.06
    ула
    -0.06
    gua
    -0.06
    	be
    -0.06
    /ca
    -0.06
    POSITIVE LOGITS
    isFunction
    0.08
     totalPages
    0.06
     exams
    0.06
     کوه
    0.06
     collections
    0.06
     DateTimeOffset
    0.06
     publicly
    0.06
    โดย
    0.06
     før
    0.06
    	edit
    0.06
    Act Density 0.178%

    No Known Activations