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
     vertices
    -0.08
    .Category
    -0.07
    .offsetWidth
    -0.07
    estatus
    -0.06
     інтерес
    -0.06
    الح
    -0.06
     debounce
    -0.06
     относят
    -0.06
     recreational
    -0.06
    |}↵
    -0.06
    POSITIVE LOGITS
    游戏
    0.07
     mold
    0.07
    аза
    0.06
     Course
    0.06
    ange
    0.06
     плав
    0.06
     beta
    0.06
    ina
    0.06
     روسی
    0.06
     documentation
    0.06
    Act Density 0.001%

    No Known Activations