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

    Neuronpedia

    INDEX
    Explanations

    C++ code

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     all
    -0.60
     Y
    -0.50
    s
    -0.47
    maten
    -0.45
     M
    -0.45
    M
    -0.45
    to
    -0.44
    <eos>
    -0.44
    ↵↵
    -0.43
    er
    -0.42
    POSITIVE LOGITS
    awtextra
    0.96
     nahilalakip
    0.95
     resourceCulture
    0.91
     समीक्षक
    0.85
    %");
    0.83
    ImageContext
    0.83
     تضيفلها
    0.82
    AccessorTable
    0.80
    parsedMessage
    0.78
     дописавши
    0.77
    Act Density 8.170%

    No Known Activations