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

    Neuronpedia

    INDEX
    Explanations

    email greetings starting with hi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    友人
    0.45
    friends
    0.43
     मित्रों
    0.42
    robot
    0.41
     пользователей
    0.41
     друзей
    0.41
    Friends
    0.41
    usuarios
    0.39
     عايز
    0.39
     bhai
    0.38
    POSITIVE LOGITS
     Orch
    0.44
     O
    0.38
     hi
    0.38
     [],
    0.38
     Low
    0.37
     목
    0.36
     Or
    0.36
     unver
    0.35
     fol
    0.35
     Roots
    0.35
    Act Density 0.008%

    No Known Activations