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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     antib
    0.49
     Pol
    0.45
    Pol
    0.42
     sh
    0.40
     pol
    0.40
     mon
    0.40
     tiny
    0.36
     int
    0.35
     odd
    0.35
     slight
    0.33
    POSITIVE LOGITS
     usuário
    2.26
     usuario
    2.22
    ovce
    2.21
    USERS
    2.17
     usuários
    2.16
    사용
    2.11
     사용자
    2.11
     gebruikers
    2.10
    使用者
    2.08
    guna
    2.07
    Act Density 0.670%

    No Known Activations