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

    Neuronpedia

    INDEX
    Explanations

    Benefit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.94
    '
    -0.57
    Архівовано
    -0.56
    脚注の使い方
    -0.52
    ’
    -0.43
    hdys
    -0.39
     also
    -0.39
     Вікіпе
    -0.39
    Literatur
    -0.39
    Jegyzetek
    -0.39
    POSITIVE LOGITS
     >=",
    0.79
     ſtate
    0.72
     houſe
    0.71
     purpoſe
    0.71
     quæ
    0.70
     ſeveral
    0.70
     iſt
    0.69
     Diſ
    0.69
    enderror
    0.68
     ſtre
    0.68
    Act Density 0.001%

    No Known Activations