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

    Neuronpedia

    INDEX
    Explanations

    the word "clear"

    oai_token-act-pair · gemini-2.0-flash

    clear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.95
     greateſt
    -0.90
     يتيمه
    -0.89
     Audiodateien
    -0.88
     ſmall
    -0.87
     Houſe
    -0.86
    +:+
    -0.86
    DockStyle
    -0.85
     ―――――
    -0.85
    出版年
    -0.84
    POSITIVE LOGITS
    <bos>
    1.53
    '
    0.75
    (
    0.64
     '
    0.63
    .
    0.62
     to
    0.62
    x
    0.60
    ↵↵
    0.59
    s
    0.59
    ’
    0.58
    Act Density 0.620%

    No Known Activations