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

    Neuronpedia

    INDEX
    Explanations

    Here's an elaboration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    建设
    0.55
     nevoie
    0.53
    𝑺
    0.52
    建成
    0.52
    áculos
    0.52
    燮
    0.51
    Фор
    0.51
    జీ
    0.49
    粮
    0.48
    देशीर
    0.48
    POSITIVE LOGITS
     </
    0.44
     ;
    0.41
     declared
    0.41
     &
    0.39
     eikä
    0.39
     私
    0.39
     zipper
    0.38
     collapsible
    0.38
     six
    0.37
     :
    0.37
    Act Density 0.003%

    No Known Activations