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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enfans
    -0.64
     påver
    -0.63
     engraçadas
    -0.60
     noires
    -0.60
     aktivitet
    -0.59
     graciosas
    -0.59
     mijne
    -0.58
     igång
    -0.57
     varandra
    -0.57
     kvinna
    -0.57
    POSITIVE LOGITS
     pinulongan
    0.87
    SourceChecksum
    0.82
     diff
    0.69
     autorytatywna
    0.67
     nahilalakip
    0.66
    GOTREF
    0.60
    findpost
    0.60
    GEBURTSDATUM
    0.58
    #+#
    0.58
     dif
    0.57
    Act Density 0.058%

    No Known Activations