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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens that include decimal points, i.e. floating-point numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	des
    -0.07
    owie
    -0.07
     Wolverine
    -0.07
     herk
    -0.06
    ินเด
    -0.06
    663
    -0.06
    elay
    -0.06
     orb
    -0.06
     gaan
    -0.06
     alist
    -0.06
    POSITIVE LOGITS
    centroid
    0.07
    ('/')↵
    0.06
     Depending
    0.06
     full
    0.06
    _ng
    0.06
    様
    0.06
     Http
    0.06
    ynamic
    0.06
    ESH
    0.06
    有限公司
    0.06
    Act Density 0.043%

    No Known Activations