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

    Neuronpedia

    INDEX
    Explanations

    grammatical particles and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     என்கிற
    0.48
     त्यानंतर
    0.47
    नाच्या
    0.47
     みたい
    0.45
    ٻ
    0.44
    ټبال
    0.44
    ليس
    0.44
    ्याच्या
    0.44
    केशन
    0.43
    णाच्या
    0.43
    POSITIVE LOGITS
    적으로
    1.10
    的に
    1.04
    で
    1.02
     में
    0.91
    에서
    0.90
    으로
    0.88
    に
    0.86
    માં
    0.86
    에
    0.83
     میں
    0.80
    Act Density 0.012%

    No Known Activations