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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Declarations
    -0.07
    著名
    -0.07
     المر
    -0.06
     dumps
    -0.06
    .FirstName
    -0.06
     Responsive
    -0.06
    下跌
    -0.06
    .UltraWin
    -0.06
    .Meta
    -0.06
    极品
    -0.06
    POSITIVE LOGITS
    莪
    0.08
    quette
    0.08
    portion
    0.07
    ottie
    0.07
     prayer
    0.07
    塆
    0.07
    她
    0.07
    dbg
    0.07
    aji
    0.07
    existence
    0.07
    Act Density 0.018%

    No Known Activations