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

    Neuronpedia

    INDEX
    Explanations

    the word "profile"

    oai_token-act-pair · gemini-2.0-flash

    profile

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.46
     myſelf
    -1.41
     purpoſe
    -1.31
    ſelf
    -1.29
     itſelf
    -1.28
     GenerationType
    -1.27
     pleaſure
    -1.27
     Reſ
    -1.27
     auffi
    -1.25
     Jefus
    -1.23
    POSITIVE LOGITS
     
    0.81
     and
    0.79
     a
    0.76
    ,
    0.75
     or
    0.66
    /
    0.64
     the
    0.63
    -
    0.63
     an
    0.63
     (
    0.63
    Act Density 1.406%

    No Known Activations