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

    Neuronpedia

    INDEX
    Explanations

    the word "the"

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.88
     myſelf
    -1.80
     Majefty
    -1.77
     itſelf
    -1.75
     raiſ
    -1.70
     Monfieur
    -1.70
    ſelf
    -1.69
     themſelves
    -1.66
     purpoſe
    -1.64
     ―――――
    -1.59
    POSITIVE LOGITS
     
    1.39
    e
    1.19
    a
    1.16
    i
    1.13
    o
    1.13
    p
    1.05
    u
    1.03
     The
    1.02
    m
    1.01
    R
    1.01
    Act Density 3.020%

    No Known Activations