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

    Neuronpedia

    INDEX
    Explanations

    numerical measurements

    oai_token-act-pair · gemini-2.0-flash

    Numbers with possible units

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.70
    脚注の使い方
    -0.69
     purpoſe
    -0.68
     Theſe
    -0.67
     >=",
    -0.67
     EconPapers
    -0.66
    ReusableCell
    -0.66
    aarrggbb
    -0.63
     дописавши
    -0.63
     MainAxisSize
    -0.62
    POSITIVE LOGITS
    <bos>
    0.80
     B
    0.47
     Ver
    0.44
     Don
    0.43
     nem
    0.43
    لق
    0.43
    ่อ
    0.43
     F
    0.42
    アン
    0.42
     Z
    0.42
    Act Density 0.590%

    No Known Activations