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

    Neuronpedia

    INDEX
    Explanations

    the word "years" and sometimes related words like "year" and "seasons."

    oai_token-act-pair · gemini-2.0-flash

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '
    -0.80
    "
    -0.77
    <strong>
    -0.70
     $
    -0.68
     "
    -0.68
    </strong>
    -0.66
     
    -0.65
    *
    -0.64
     months
    -0.64
     D
    -0.63
    POSITIVE LOGITS
     houſe
    1.29
     Efq
    1.25
     purpoſe
    1.22
     Theſe
    1.20
     Houſe
    1.16
     myſelf
    1.13
     ſtate
    1.09
     itſelf
    1.08
     Majefty
    1.05
     greateſt
    1.05
    Act Density 0.559%

    No Known Activations