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

    Neuronpedia

    INDEX
    Explanations

    ates suffix

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    郑
    -0.07
    STER
    -0.06
     폴
    -0.06
    ...
    -0.06
    YOUR
    -0.06
     cricket
    -0.06
    ，你
    -0.06
     Coupons
    -0.06
     تكييف
    -0.06
     Household
    -0.06
    POSITIVE LOGITS
    -sectional
    0.07
     vel
    0.06
    	atomic
    0.06
    ジア
    0.06
     hallmark
    0.06
     Showcase
    0.06
     Hawth
    0.06
     Sb
    0.06
     emo
    0.06
     Vel
    0.06
    Act Density 0.012%

    No Known Activations