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

    Neuronpedia

    INDEX
    Explanations

    say "_train"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蟠
    -0.08
    お願
    -0.07
    🤥
    -0.07
    فد
    -0.07
    珙
    -0.07
     كان
    -0.07
     COMM
    -0.07
     Madden
    -0.07
    宦
    -0.07
    Ⲫ
    -0.06
    POSITIVE LOGITS
    redirect
    0.07
    /debug
    0.07
    智慧
    0.07
    数据
    0.07
     elbow
    0.07
    скую
    0.07
     </
    0.07
    -Americ
    0.07
    asto
    0.07
    ´
    0.07
    Act Density 0.002%

    No Known Activations