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

    Neuronpedia

    INDEX
    Explanations

    brands and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     McKinsey
    0.55
     Bloomberg
    0.54
     Accenture
    0.53
    Bloomberg
    0.52
     concierge
    0.50
    neyland
    0.49
     Barclays
    0.48
    Dropbox
    0.46
     uber
    0.45
     Premiership
    0.45
    POSITIVE LOGITS
     Xiaomi
    0.60
     AliExpress
    0.58
     Xin
    0.57
     Aliexpress
    0.57
     Z
    0.57
     Redmi
    0.55
     Xia
    0.54
     Hong
    0.53
     Yi
    0.50
     Hua
    0.50
    Act Density 0.010%

    No Known Activations