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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cust
    -0.07
    𝘫
    -0.07
     diesel
    -0.07
     chàng
    -0.07
    ,cljs
    -0.07
     השימוש
    -0.07
    -co
    -0.07
     ela
    -0.06
     lame
    -0.06
     Gust
    -0.06
    POSITIVE LOGITS
    пущен
    0.07
    定居
    0.07
    	conf
    0.07
     halfway
    0.07
     collector
    0.07
     ground
    0.07
     run
    0.07
    幫助
    0.07
    敬请
    0.07
    也不要
    0.07
    Act Density 0.001%

    No Known Activations