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

    Neuronpedia

    INDEX
    Explanations

    fit

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on numeric literals—especially decimal numbers—within the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    "
    -0.06
     nearing
    -0.06
     wur
    -0.06
     fj
    -0.06
     Raider
    -0.06
    .','
    -0.06
    ющ
    -0.06
     tragic
    -0.06
    verige
    -0.06
    	obj
    -0.06
    POSITIVE LOGITS
    ्ज
    0.07
    _iterator
    0.06
     Müş
    0.06
     allowing
    0.06
    aver
    0.06
    (let
    0.06
    老师
    0.06
     vět
    0.06
     hopeless
    0.06
    onenumber
    0.06
    Act Density 0.426%

    No Known Activations