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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of quantitative information—numbers, counts, percentages, and other numeric or enumerative terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Eduardo
    -0.08
     robbery
    -0.07
     dương
    -0.07
    .duration
    -0.07
    -government
    -0.07
     Ruf
    -0.06
     Justin
    -0.06
    /system
    -0.06
    _linear
    -0.06
    ठ
    -0.06
    POSITIVE LOGITS
     أي
    0.07
     ayak
    0.07
    	Service
    0.06
     ®
    0.06
     招
    0.06
     國
    0.06
     {},↵
    0.06
    ]]>
    0.06
    竞
    0.06
     henne
    0.06
    Act Density 0.030%

    No Known Activations