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

    Neuronpedia

    INDEX
    Explanations

    verbs and common suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    身份
    0.26
    StarGo
    0.25
    တဲ့
    0.24
     عدالت
    0.24
     Spaß
    0.23
     nerdy
    0.23
    들을
    0.23
    ارهای
    0.23
     ज्यादा
    0.23
     cái
    0.22
    POSITIVE LOGITS
    ce
    0.30
    th
    0.27
    er
    0.26
    dr
    0.26
    ol
    0.26
    ě
    0.25
    á
    0.25
    se
    0.24
    re
    0.24
     ten
    0.24
    Act Density 0.119%

    No Known Activations