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

    Neuronpedia

    INDEX
    Explanations

    Punctuation and Chinese

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쉴
    -0.07
     zrobić
    -0.07
    arra
    -0.07
     Different
    -0.07
    ворот
    -0.07
    贴心
    -0.07
    mort
    -0.07
     новый
    -0.07
    tility
    -0.07
    少不了
    -0.07
    POSITIVE LOGITS
    1
    0.22
     of
    0.18
    ↵↵
    0.18
    的
    0.17
    .↵
    0.16
    .↵↵
    0.16
    ↵
    0.16
     (
    0.14
    ↵
    0.14
    。↵
    0.14
    Act Density 12.315%

    No Known Activations