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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ethernet
    -0.07
    nodoc
    -0.06
    382
    -0.06
     identification
    -0.06
    人类
    -0.06
     contractors
    -0.06
    노출
    -0.06
    our
    -0.06
     Grace
    -0.06
     forfeiture
    -0.06
    POSITIVE LOGITS
     Baths
    0.06
    CLOCKS
    0.06
    aucoup
    0.06
     chimney
    0.06
     african
    0.06
    تون
    0.06
     eBay
    0.06
     --↵
    0.06
     Records
    0.06
    	when
    0.06
    Act Density 0.001%

    No Known Activations