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

    Neuronpedia

    INDEX
    Explanations

    the word "alike", and sometimes activates on associated words.

    oai_token-act-pair · gemini-2.0-flash

    alike

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     As
    -0.76
     I
    -0.66
    tably
    -0.65
     For
    -0.65
    withstanding
    -0.65
    </blockquote>
    -0.63
    alyptus
    -0.63
     Or
    -0.62
    åringen
    -0.62
     W
    -0.61
    POSITIVE LOGITS
     Theſe
    1.30
     avoient
    1.16
     ainfi
    1.16
     étoient
    1.10
     auffi
    1.08
     enfans
    1.06
     Efq
    1.02
     Beſ
    1.01
     étoit
    1.00
     quæ
    1.00
    Act Density 2.278%

    No Known Activations