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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unig
    -0.08
     حسب
    -0.08
     shortlist
    -0.08
     [/
    -0.08
     ternyata
    -0.08
     يعتبر
    -0.08
    ส่วน
    -0.08
     الصفحة
    -0.08
     upfront
    -0.08
     cashback
    -0.07
    POSITIVE LOGITS
     будто
    0.10
     jemand
    0.09
    有人
    0.09
     Guardians
    0.08
    adeira
    0.08
     embarking
    0.08
    人在
    0.08
     peeling
    0.08
     rebels
    0.08
     fishermen
    0.08
    Act Density 0.018%

    No Known Activations