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

    Neuronpedia

    INDEX
    Explanations

    numbers containing 9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MUS
    0.32
    ैसे
    0.28
     Bere
    0.28
     preference
    0.27
     পৌছ
    0.27
    TEST
    0.27
     সংসারের
    0.27
     Alh
    0.27
     BOOLE
    0.27
    ()
    0.26
    POSITIVE LOGITS
    かと思います
    0.33
     zunächst
    0.33
    दै
    0.33
     tér
    0.32
    स्तो
    0.31
     înainte
    0.31
     abz
    0.30
     امریکہ
    0.30
    tois
    0.30
     書い
    0.30
    Act Density 0.010%

    No Known Activations