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

    Neuronpedia

    INDEX
    Explanations

    "a good way"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    髂
    0.43
     ähn
    0.41
    下記の
    0.40
    下記
    0.39
    Nord
    0.39
    ต่ำ
    0.38
    FindingsRequest
    0.38
    高的
    0.37
     иллюстра
    0.37
    স
    0.37
    POSITIVE LOGITS
     Одна
    0.43
     thanks
    0.43
     পেয়েছেন
    0.42
     venues
    0.42
     믿
    0.42
     Harvest
    0.40
     什么
    0.40
     즐
    0.40
     kosong
    0.40
     Get
    0.39
    Act Density 0.001%

    No Known Activations