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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )arg
    -0.07
    葳
    -0.07
    рак
    -0.07
     merchants
    -0.06
    _Construct
    -0.06
     constitutional
    -0.06
     cornerstone
    -0.06
     Männer
    -0.06
     functions
    -0.06
    )test
    -0.06
    POSITIVE LOGITS
     PAY
    0.08
     xlim
    0.07
    Њ
    0.07
     الكمبي
    0.07
     אפשר
    0.07
     يقدم
    0.07
    火锅
    0.07
    辣椒
    0.07
     stressful
    0.07
     Stamford
    0.06
    Act Density 0.001%

    No Known Activations