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

    Neuronpedia

    INDEX
    Explanations

    mor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comport
    -0.07
    .until
    -0.07
    Au
    -0.07
     alguna
    -0.06
    gambar
    -0.06
     hukuk
    -0.06
    �
    -0.06
     얼굴
    -0.06
    Thông
    -0.06
     Cater
    -0.06
    POSITIVE LOGITS
    典
    0.07
    。「
    0.06
     germ
    0.06
     newY
    0.06
     Ebook
    0.06
    Г
    0.06
    ().↵
    0.06
    “.
    0.06
    /default
    0.06
    ､_
    0.06
    Act Density 0.018%

    No Known Activations