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

    Neuronpedia

    INDEX
    Explanations

    the word "properly"

    oai_token-act-pair · gemini-2.0-flash

    properly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.84
    </i>
    -0.83
    </b>
    -0.82
    '
    -0.77
    ..
    -0.74
    `
    -0.71
    al
    -0.71
    t
    -0.70
    i
    -0.70
     K
    -0.69
    POSITIVE LOGITS
     myſelf
    2.30
     Monfieur
    2.19
     Majefty
    2.14
     Jefus
    2.06
     Efq
    2.05
     themſelves
    2.03
     Houſe
    2.03
     itſelf
    2.02
    ſelf
    1.98
     Reſ
    1.98
    Act Density 1.698%

    No Known Activations