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

    Neuronpedia

    INDEX
    Explanations

    professional roles

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    绉
    0.65
     Tetrahedron
    0.64
     использования
    0.58
     utilising
    0.58
    electrolyte
    0.57
     位置
    0.56
     learning
    0.55
    ट्
    0.55
     Ending
    0.54
     Know
    0.54
    POSITIVE LOGITS
    recover
    0.57
     স্কোর
    0.57
     aseguró
    0.55
     fugiat
    0.55
     এগুলো
    0.54
    önes
    0.54
     tranquila
    0.53
     così
    0.53
     logró
    0.53
     gig
    0.52
    Act Density 0.000%

    No Known Activations