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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seminars
    -0.07
     پش
    -0.07
    	cli
    -0.06
     mekt
    -0.06
     zn
    -0.06
    گی
    -0.06
    红
    -0.06
     held
    -0.06
    .tracks
    -0.06
    idea
    -0.06
    POSITIVE LOGITS
     العق
    0.06
    毛
    0.06
     абсолютно
    0.06
    ates
    0.06
     MONTH
    0.06
     سنگ
    0.06
     className
    0.06
    ()];↵
    0.06
     boj
    0.06
    ально
    0.06
    Act Density 0.001%

    No Known Activations