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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (signal
    -0.07
    َد
    -0.07
     boast
    -0.06
    ตรง
    -0.06
     کوه
    -0.06
    _operations
    -0.06
     adım
    -0.06
    _parsed
    -0.06
     buildup
    -0.06
    áo
    -0.06
    POSITIVE LOGITS
    techn
    0.07
    Registro
    0.07
    ванов
    0.06
    Then
    0.06
    unread
    0.06
     joystick
    0.06
    τέ
    0.06
     ثابت
    0.06
     Tiffany
    0.06
     захворю
    0.06
    Act Density 0.133%

    No Known Activations