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

    Neuronpedia

    INDEX
    Explanations

    not a limitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thoughtfully
    0.39
    стом
    0.38
    Suggested
    0.38
     бе
    0.38
    तियों
    0.38
     Ин
    0.38
     можем
    0.38
     краси
    0.37
    рые
    0.37
    Mood
    0.37
    POSITIVE LOGITS
    តែ
    0.47
    mailer
    0.47
     Brewster
    0.47
     heller
    0.46
     اسكت
    0.46
     arbeids
    0.46
    oyloxy
    0.45
    ethoven
    0.45
    ضغط
    0.45
    cester
    0.45
    Act Density 0.010%

    No Known Activations