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

    Neuronpedia

    INDEX
    Explanations

    ](

    np_max-act · gemini-2.0-flash

    The neuron activates on inline references to figures and tables (e.g. “Figure 2,” “Fig. 1,” “Table 1”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Laure
    -0.07
    .choose
    -0.07
    енными
    -0.06
    наслід
    -0.06
    Marshal
    -0.06
    uess
    -0.06
    スの
    -0.06
     [#
    -0.06
     Heap
    -0.06
     Past
    -0.06
    POSITIVE LOGITS
     Numerous
    0.06
    destruct
    0.06
    arging
    0.06
    --,
    0.06
     زیاد
    0.06
    max
    0.06
     Relative
    0.06
     modifiers
    0.06
    ้อ
    0.06
     tz
    0.06
    Act Density 0.002%

    No Known Activations