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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns in German

    oai_token-act-pair · gemini-2.0-flash

    man

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     виправивши
    -1.11
     Anſ
    -1.05
     myſelf
    -1.04
     Diſ
    -0.98
     Reſ
    -0.96
     itſelf
    -0.96
     anſ
    -0.95
     himſelf
    -0.94
     Theſe
    -0.94
    ſelf
    -0.93
    POSITIVE LOGITS
    </i>
    0.60
    “
    0.60
    [
    0.59
    </b>
    0.58
    "
    0.56
    ',
    0.52
     a
    0.50
    (
    0.50
    <bos>
    0.49
    |
    0.49
    Act Density 2.189%

    No Known Activations