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

    Neuronpedia

    INDEX
    Explanations

    construction and repair

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.30
     myſelf
    -1.28
     Majefty
    -1.24
     ſtate
    -1.23
     pleaſure
    -1.19
     ſmall
    -1.16
     greateſt
    -1.16
     crdi
    -1.16
     ſeveral
    -1.14
     Houſe
    -1.12
    POSITIVE LOGITS
    ↵↵
    0.81
    '
    0.76
    ,
    0.69
    ↵
    0.62
     and
    0.60
    .
    0.60
     to
    0.58
     
    0.57
    "
    0.57
    /
    0.56
    Act Density 0.049%

    No Known Activations