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

    Neuronpedia

    INDEX
    Explanations

    introductions and disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propOrder
    -0.71
     be
    -0.65
     nahilalakip
    -0.62
     get
    -0.60
     estimés
    -0.59
     do
    -0.57
    GEBURTSDATUM
    -0.56
     prove
    -0.54
    rungsseite
    -0.54
     provide
    -0.51
    POSITIVE LOGITS
     purpoſe
    0.85
     greateſt
    0.84
     pleaſure
    0.84
     ſmall
    0.82
     Jefus
    0.81
     Chriſt
    0.81
     ſeveral
    0.77
     houſe
    0.76
     Majefty
    0.76
     étoit
    0.75
    Act Density 0.014%

    No Known Activations