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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     julho
    1.15
     caráter
    1.10
     conceit
    1.07
     mulheres
    0.99
     Projet
    0.98
     hayat
    0.98
     unab
    0.96
     dezembro
    0.96
     engulfed
    0.96
     Ví
    0.96
    POSITIVE LOGITS
    ו
    1.02
    e
    1.01
    weixin
    0.87
    \{-
    0.86
     [
    0.86
    u
    0.85
    0.84
    ισ
    0.82
    წი
    0.81
    서
    0.80
    Act Density 0.000%

    No Known Activations