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

    Neuronpedia

    INDEX
    Explanations

    first person pronouns like I, me, and my

    oai_token-act-pair · gemini-2.0-flash

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.86
    Personensuche
    -0.66
    DoubleQuotes
    -0.57
     they
    -0.54
     I
    -0.50
     we
    -0.48
     ویکی‌پدی
    -0.47
    #
    -0.46
     you
    -0.45
    uleiro
    -0.44
    POSITIVE LOGITS
     BrowserModule
    0.62
    ollectionView
    0.56
    0.56
    存于互联网档案馆
    0.55
    ……"
    0.55
     onOptions
    0.54
    UserScript
    0.54
    Tikang
    0.54
    AxisAlignment
    0.54
     \%}$
    0.53
    Act Density 1.422%

    No Known Activations