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

    Neuronpedia

    INDEX
    Explanations

    standup comedy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.82
    s
    0.66
    u
    0.61
    ('
    0.60
    m
    0.60
    「
    0.58
    g
    0.57
    ("
    0.56
    '>
    0.56
    ti
    0.56
    POSITIVE LOGITS
    ید
    0.65
    ى
    0.55
     Meld
    0.55
    ور
    0.54
    ่อย
    0.54
     書い
    0.53
     друзья
    0.52
     Filme
    0.52
     IntelliJ
    0.52
    ிகளை
    0.52
    Act Density 0.001%

    No Known Activations