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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash

    phrases related to sound quality and audio performance in hardware reviews.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on comparative constructions that express “more/less X than Y” (e.g. “supérieur à,” “plus que,” “better than”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     respondents
    -0.05
    olut
    -0.05
     часа
    -0.05
     оброб
    -0.05
     Mik
    -0.05
    oe
    -0.05
    	opt
    -0.05
    よ
    -0.05
    rowData
    -0.05
     gifts
    -0.05
    POSITIVE LOGITS
    ließlich
    0.08
     spanish
    0.08
     cine
    0.07
     ―
    0.07
     defaultProps
    0.07
     структу
    0.07
    콩
    0.07
     عدم
    0.07
     II
    0.06
    (AF
    0.06
    Act Density 0.036%

    No Known Activations