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

    Neuronpedia

    INDEX
    Explanations

    list headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مسائل
    0.41
     remodel
    0.41
     পদ্ধতিতে
    0.41
    間の
    0.40
     Mainz
    0.40
     Вул
    0.40
    ទាំង
    0.39
     ordine
    0.39
    軾
    0.39
    手段
    0.38
    POSITIVE LOGITS
     и
    0.45
    顫
    0.42
    це
    0.41
     మరియు
    0.41
     şi
    0.40
    is
    0.40
    었고
    0.39
    最低
    0.39
     July
    0.39
     आणि
    0.39
    Act Density 0.000%

    No Known Activations