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

    Neuronpedia

    INDEX
    Explanations

    Accented words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ರುಗ
    0.51
     سنه
    0.50
    σεων
    0.48
     الخامسه
    0.48
    nicheskij
    0.46
    夼
    0.46
    حه
    0.45
     रतन
    0.45
    킁
    0.45
     પ્રિય
    0.45
    POSITIVE LOGITS
     Ré
    1.12
     Bé
    1.12
    Má
    1.10
    É
    1.09
     Lé
    1.08
     Dé
    1.07
    Ré
    1.06
     Má
    1.06
     RÉ
    1.05
    Dé
    1.05
    Act Density 0.103%

    No Known Activations