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

    Neuronpedia

    INDEX
    Explanations

    rug

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𬬱
    -0.08
     prepared
    -0.07
    .unsplash
    -0.07
    菀
    -0.07
     nhị
    -0.07
    孕妇
    -0.07
    ктив
    -0.07
     Milo
    -0.07
    圃
    -0.07
    更快
    -0.07
    POSITIVE LOGITS
    .timeout
    0.07
    箩
    0.07
    ewhat
    0.07
    "},
↵
    0.07
    遇到
    0.07
     ole
    0.07
    上看
    0.07
    implementation
    0.06
    (month
    0.06
    '},↵
    0.06
    Act Density 0.002%

    No Known Activations