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

    Neuronpedia

    INDEX
    Explanations

    bib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bỏ
    -0.07
     кра
    -0.07
    GetType
    -0.07
     essay
    -0.06
    电
    -0.06
    _classifier
    -0.06
    咲
    -0.06
     koji
    -0.06
    -sale
    -0.06
     Sonra
    -0.06
    POSITIVE LOGITS
     νεφώσεις
    0.07
    	namespace
    0.06
     Countdown
    0.06
     Bobby
    0.06
     Fortunately
    0.06
    џЭ
    0.06
    Coupon
    0.06
     receptions
    0.06
     inefficient
    0.06
     firefighters
    0.05
    Act Density 0.001%

    No Known Activations