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

    Neuronpedia

    INDEX
    Explanations

    the word "most"

    oai_token-act-pair · gemini-2.0-flash

    most

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.03
     “
    -0.68
     
    -0.68
     the
    -0.66
    <em>
    -0.65
     "
    -0.64
    -
    -0.61
    “
    -0.61
    '
    -0.59
    go
    -0.58
    POSITIVE LOGITS
     Efq
    1.42
     myſelf
    1.34
     Anſ
    1.29
     Eſ
    1.27
     Majefty
    1.23
     Houſe
    1.23
    تقاوى
    1.23
     itſelf
    1.22
     Jefus
    1.20
     Reſ
    1.20
    Act Density 0.367%

    No Known Activations