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

    Neuronpedia

    INDEX
    Explanations

    code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лке
    0.39
    בּ
    0.37
     গৃহ
    0.37
    uchte
    0.37
    بري
    0.36
    ܬ
    0.36
    氯
    0.36
    Chlor
    0.35
    ிற்கு
    0.35
    ikat
    0.35
    POSITIVE LOGITS
     />
    0.42
     essential
    0.38
     thoughts
    0.38
     fresh
    0.38
     times
    0.37
     Poker
    0.37
     Ball
    0.36
     Ko
    0.36
     rich
    0.36
    ..
    0.35
    Act Density 0.009%

    No Known Activations