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

    Neuronpedia

    INDEX
    Explanations

    owe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الحر
    -0.08
    퓪
    -0.07
     Buzz
    -0.07
     법
    -0.07
    石化
    -0.07
    立法
    -0.07
    ☘
    -0.07
     Hop
    -0.07
     enlightenment
    -0.06
    /dist
    -0.06
    POSITIVE LOGITS
    incess
    0.08
    ﮥ
    0.07
    Lua
    0.07
    âu
    0.07
    发生的
    0.07
    واشن
    0.07
     small
    0.07
    iasi
    0.06
     <->
    0.06
    剟
    0.06
    Act Density 0.004%

    No Known Activations