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

    Neuronpedia

    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doch
    -0.07
    leted
    -0.06
    -dat
    -0.06
     인기
    -0.06
    .desktop
    -0.06
    clusion
    -0.06
    一点
    -0.06
    ニ
    -0.06
     MSD
    -0.06
    เธ
    -0.06
    POSITIVE LOGITS
    .getDeclared
    0.07
     타
    0.07
    ROS
    0.06
    (handles
    0.06
    pay
    0.06
    اءات
    0.06
    PathParam
    0.06
    ');
↵
    0.06
    >";↵
    0.06
     çağ
    0.06
    Act Density 0.004%

    No Known Activations