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

    Neuronpedia

    INDEX
    Explanations

    quite as, same level as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सुविधाओं
    0.77
    ὸς
    0.73
    まさに
    0.73
     tatsächlich
    0.73
     буквально
    0.73
     complicate
    0.73
     actual
    0.72
    ۋ
    0.71
    实质
    0.71
    порта
    0.71
    POSITIVE LOGITS
     lika
    1.56
    那麼
    1.39
     so
    1.37
    那么
    1.33
     उतना
    1.32
     same
    1.29
     उतनी
    1.19
     genauso
    1.19
     তত
    1.13
     anymore
    1.12
    Act Density 0.096%

    No Known Activations