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

    Neuronpedia

    INDEX
    Explanations

    figure/table references

    np_max-act · gemini-2.0-flash

    The neuron fires on inline numeric labels for figures or tables (e.g. the “Fig. 1” or “Tab 1” reference tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     revenge
    -0.07
    <s
    -0.07
     CM
    -0.06
    	com
    -0.06
     Interactive
    -0.06
     corros
    -0.06
     sigu
    -0.06
     Όμιλος
    -0.06
    이터
    -0.06
     antibiot
    -0.06
    POSITIVE LOGITS
    دمة
    0.07
    /div
    0.06
    ornecedor
    0.06
     सन
    0.06
    Uh
    0.06
    tplib
    0.06
     \'
    0.06
    (Initialized
    0.06
     Закону
    0.06
    ковые
    0.06
    Act Density 0.003%

    No Known Activations