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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on numeric expressions—especially decimal numbers and measurement/statistical values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    laden
    -0.07
    	layer
    -0.07
     inhibitor
    -0.07
    612
    -0.07
    列表
    -0.06
    Để
    -0.06
    tile
    -0.06
    Floor
    -0.06
    elist
    -0.06
    ++↵
    -0.06
    POSITIVE LOGITS
     Adds
    0.07
     qry
    0.07
     QGraphics
    0.06
    implements
    0.06
    ISMATCH
    0.06
    $('#
    0.06
     whose
    0.06
     termed
    0.06
    .getPrice
    0.06
     styling
    0.06
    Act Density 0.068%

    No Known Activations