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

    Neuronpedia

    INDEX
    Explanations

    say "to"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    3.61
    to
    2.84
    To
    2.30
     To
    2.28
     إلى
    2.11
    到
    2.01
     TO
    1.78
     الى
    1.73
     để
    1.70
     not
    1.69
    POSITIVE LOGITS
     עבור
    0.75
    ບບ
    0.70
    issante
    0.70
    ố
    0.67
     উপলক্ষে
    0.66
     የሚ
    0.65
     হওয়া
    0.63
    usnya
    0.63
    sinya
    0.62
    带来了
    0.61
    Act Density 0.353%

    No Known Activations