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

    Neuronpedia

    INDEX
    Explanations

    patent/technical writing

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (including decimal points and digit sequences).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sly
    -0.07
    Coll
    -0.06
     ada
    -0.06
     řád
    -0.06
    -ins
    -0.06
    اشة
    -0.06
    counter
    -0.06
     decals
    -0.06
    eceğiz
    -0.06
    "<?
    -0.06
    POSITIVE LOGITS
    igen
    0.08
    icopt
    0.06
    TECTION
    0.06
     nextPage
    0.06
    ･
    0.06
     OnePlus
    0.06
     batt
    0.06
     kaybet
    0.06
    ceived
    0.06
    keiten
    0.06
    Act Density 0.047%

    No Known Activations