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

    Neuronpedia

    INDEX
    Explanations

    words with 's' endings, possessive pronouns, and words like 'such', 'both', and 'other'

    oai_token-act-pair · gemini-2.0-flash

    alternatives and choices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ſeveral
    -0.94
     diſt
    -0.90
     ſtand
    -0.87
     pleaſure
    -0.86
     ſta
    -0.85
     myſelf
    -0.84
     Majefty
    -0.84
     ſmall
    -0.82
     Reſ
    -0.82
     ſte
    -0.82
    POSITIVE LOGITS
    ,
    0.68
     it
    0.53
    -
    0.52
    '
    0.52
     choisissez
    0.49
    ’
    0.49
     cima
    0.47
     оригіналу
    0.47
     pourrais
    0.45
    ize
    0.44
    Act Density 1.376%

    No Known Activations