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

    Neuronpedia

    INDEX
    Explanations

    code or math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ;;^
    -0.08
    ✺
    -0.07
    认
    -0.07
     chuyến
    -0.07
     thự
    -0.07
     chỉnh
    -0.07
    我相信
    -0.06
     Drone
    -0.06
     Extension
    -0.06
    ✍
    -0.06
    POSITIVE LOGITS
    XXXX
    0.07
    омер
    0.07
    политическ
    0.07
    靡
    0.07
    DC
    0.07
    >())↵
    0.06
    Detach
    0.06
     earthly
    0.06
    NW
    0.06
    postData
    0.06
    Act Density 0.053%

    No Known Activations