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

    Neuronpedia

    INDEX
    Explanations

    business and law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -1.32
     itſelf
    -1.08
    出版年
    -1.07
     ſmall
    -1.07
     pleaſure
    -1.07
     Monfieur
    -1.07
     Jefus
    -1.05
     houſe
    -1.05
     greateſt
    -1.03
     الحره
    -1.02
    POSITIVE LOGITS
     
    0.60
    (
    0.49
     l
    0.46
    '
    0.46
     c
    0.45
    -
    0.45
     or
    0.42
     I
    0.42
     la
    0.41
     k
    0.41
    Act Density 0.054%

    No Known Activations