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

    Neuronpedia

    INDEX
    Explanations

    the word "as" in a variety of contexts

    oai_token-act-pair · gemini-2.0-flash

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.22
    ^(@)
    -1.20
    ſelf
    -1.13
     Majefty
    -1.12
    ſelves
    -1.07
     houſe
    -1.05
     ſeveral
    -1.05
     myſelf
    -1.03
     greateſt
    -1.03
     reaſon
    -1.02
    POSITIVE LOGITS
    <bos>
    1.53
    '
    0.96
    ↵
    0.91
    ↵↵
    0.85
    ’
    0.81
    a
    0.80
    "
    0.76
    n
    0.76
    1
    0.74
    ↵↵↵
    0.73
    Act Density 0.441%

    No Known Activations