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

    Neuronpedia

    INDEX
    Explanations

    just wow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AE
    0.41
     lũ
    0.40
    埴
    0.38
     negligent
    0.38
     contradiction
    0.37
    朿
    0.36
    矛盾
    0.35
     contradictory
    0.35
     optimizing
    0.35
     optimize
    0.35
    POSITIVE LOGITS
     wow
    3.69
     Wow
    3.61
    Wow
    3.47
     WOW
    3.42
    wow
    3.27
    WOW
    3.17
     WoW
    2.36
    哇
    1.62
     dazz
    1.45
     awe
    1.33
    Act Density 0.022%

    No Known Activations