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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    The neuron never fires—it remains inactive on all inputs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    検
    -0.06
    los
    -0.06
    <HashMap
    -0.06
    Expired
    -0.06
    ляють
    -0.06
    襲
    -0.06
    icus
    -0.06
    sei
    -0.06
    intl
    -0.06
    ije
    -0.06
    POSITIVE LOGITS
     Buck
    0.07
     #↵
    0.07
     discard
    0.07
    ----
    0.06
     　
    0.06
    非常
    0.06
    Это
    0.06
    -ahead
    0.06
     knitting
    0.06
    {↵
    0.06
    Act Density 0.018%

    No Known Activations