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

    Neuronpedia

    INDEX
    Explanations

    LaTeX code formatting

    oai_token-act-pair · gemini-2.0-flash

    scientific papers formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vikipedi
    -0.77
    出版年
    -0.75
     виправивши
    -0.73
    "},
    -0.72
    Przypisy
    -0.71
    AlterField
    -0.70
    DeleteBehavior
    -0.69
     pinulongan
    -0.69
    ็จ
    -0.68
    mbggenerated
    -0.68
    POSITIVE LOGITS
    ↵↵
    0.60
    RenderAtEndOf
    0.52
    ↵
    0.42
    Olá
    0.41
    The
    0.39
    sizeCache
    0.39
    .
    0.39
    Si
    0.39
    かが
    0.38
    En
    0.38
    Act Density 0.448%

    No Known Activations