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

    Neuronpedia

    INDEX
    Explanations

    various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    0.44
    0.36
     нередко
    0.36
     instaur
    0.34
     bzw
    0.31
     convivencia
    0.30
     pourra
    0.30
     illetve
    0.30
     Alltag
    0.30
     ഏറെ
    0.29
    POSITIVE LOGITS
     అతను
    0.42
    একটি
    0.42
     ambayo
    0.40
     ඔහුගේ
    0.40
     უფრო
    0.39
    archiwizowane
    0.39
    帐户
    0.38
     അല്ലെങ്കിൽ
    0.38
    உங்கள்
    0.37
     লোকেরা
    0.37
    Act Density 0.014%

    No Known Activations