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

    Neuronpedia

    INDEX
    Explanations

    adverbs ending in ly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ótima
    0.90
    ুয়াল
    0.90
    려는
    0.88
    нкү
    0.85
     precise
    0.81
     인한
    0.80
    ارع
    0.80
     Unreal
    0.79
     ausreiche
    0.79
    नातील
    0.78
    POSITIVE LOGITS
    ly
    2.85
    ously
    2.64
    적으로
    2.60
    ically
    2.55
    ally
    2.51
    ively
    2.41
    ently
    2.40
    的に
    2.39
    arily
    2.38
    fully
    2.38
    Act Density 0.229%

    No Known Activations