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

    Neuronpedia

    INDEX
    Explanations

    decades

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ירות
    -0.07
     Mud
    -0.07
    对不起
    -0.07
    Cog
    -0.07
     vip
    -0.07
     mistress
    -0.07
    _card
    -0.07
    مين
    -0.07
    积极响应
    -0.07
    .RelativeLayout
    -0.07
    POSITIVE LOGITS
     decades
    0.07
     видео
    0.07
    ㄚ
    0.07
     Jak
    0.07
    马上就
    0.07
     Expanded
    0.07
     ориг
    0.07
    /l
    0.06
    haul
    0.06
     debuted
    0.06
    Act Density 0.008%

    No Known Activations