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

    Neuronpedia

    INDEX
    Explanations

    and tell me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不安
    0.47
     Вообще
    0.43
    导致的
    0.43
    Entonces
    0.41
     Тогда
    0.41
     gira
    0.40
     waardoor
    0.40
    噉
    0.40
     совсем
    0.40
    それが
    0.39
    POSITIVE LOGITS
     youll
    0.53
    我们会
    0.53
    我們會
    0.53
     we
    0.53
    我们将
    0.48
     you
    0.46
     will
    0.43
     අපි
    0.43
    йте
    0.42
     akan
    0.41
    Act Density 0.021%

    No Known Activations