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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash

    This neuron detects quantitative measurements—numbers (and associated symbols/units) in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ukes
    -0.07
    _marks
    -0.07
     coordinator
    -0.07
    aked
    -0.06
    出品者
    -0.06
     rowspan
    -0.06
    Incomplete
    -0.06
    _AV
    -0.06
    greater
    -0.06
    ourcing
    -0.06
    POSITIVE LOGITS
    /connection
    0.06
    .…
    0.06
     Blast
    0.06
     böylece
    0.06
    ::::::::::::::::::::::::::::::::
    0.06
     Coco
    0.06
    HORT
    0.06
    published
    0.06
     Meals
    0.06
    /material
    0.06
    Act Density 0.027%

    No Known Activations