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

    Neuronpedia

    INDEX
    Explanations

    the word "no"

    oai_token-act-pair · gemini-2.0-flash

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ſeveral
    -0.69
     Majefty
    -0.68
    belec
    -0.67
     Sopho
    -0.62
     Suivez
    -0.60
     diſt
    -0.60
     Eccle
    -0.59
     Zeno
    -0.59
     pilgri
    -0.58
    lück
    -0.58
    POSITIVE LOGITS
    <bos>
    0.80
     “
    0.68
     ‘
    0.58
    “
    0.57
     the
    0.53
    مصادر
    0.50
     c
    0.50
    ’
    0.48
     not
    0.48
    endregion
    0.48
    Act Density 0.860%

    No Known Activations