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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brun
    -0.65
     pas
    -0.63
     im
    -0.60
     Fer
    -0.59
     int
    -0.58
     Fe
    -0.57
     Fry
    -0.56
     Ber
    -0.56
     ma
    -0.56
     Luc
    -0.55
    POSITIVE LOGITS
     étoient
    1.03
     avoient
    1.02
     Jefus
    0.94
     feroit
    0.94
     Monfieur
    0.94
     iſt
    0.91
     Theſe
    0.91
    guien
    0.90
     étoit
    0.90
     nôtre
    0.90
    Act Density 0.058%

    No Known Activations