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

    Neuronpedia

    INDEX
    Explanations

    Games and guessing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     readily
    0.89
    容易
    0.89
     особенно
    0.82
     especially
    0.80
     dễ
    0.78
     easily
    0.78
     facilmente
    0.78
     오히려
    0.78
    むしろ
    0.77
    很容易
    0.74
    POSITIVE LOGITS
     đoán
    1.07
     teams
    1.00
     guessing
    0.99
    팀
    0.97
     guess
    0.95
    guess
    0.92
     Guess
    0.92
     Punkten
    0.91
     punten
    0.91
     puan
    0.91
    Act Density 0.257%

    No Known Activations