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

    Neuronpedia

    INDEX
    Explanations

    Death

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    喆
    -0.07
    需要注意
    -0.07
    _encoded
    -0.07
    ключ
    -0.07
     deren
    -0.07
    .functions
    -0.07
     requer
    -0.07
    .Xna
    -0.07
    коло
    -0.07
    response
    -0.07
    POSITIVE LOGITS
    >J
    0.07
    减肥
    0.07
     Barr
    0.06
    -length
    0.06
    っている
    0.06
    落后
    0.06
    态度
    0.06
    体质
    0.06
    staking
    0.06
     flag
    0.06
    Act Density 0.077%

    No Known Activations