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

    Neuronpedia

    INDEX
    Explanations

    how to make

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    म
    1.06
    Lemma
    0.96
    ৩৩
    0.93
    MenuStyle
    0.89
    唳
    0.89
     Hölder
    0.88
    Ethan
    0.86
    س
    0.86
    ความ
    0.86
    خ
    0.86
    POSITIVE LOGITS
     dàng
    0.85
    પણે
    0.82
     Pick
    0.82
     homeschool
    0.80
     Subhanahu
    0.80
     darn
    0.80
    ів
    0.79
    á
    0.79
    。
    0.79
     un
    0.77
    Act Density 0.000%

    No Known Activations