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

    Neuronpedia

    INDEX
    Explanations

    potential conflict or section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    と
    0.44
    ●
    0.44
    ニュース
    0.43
    ناع
    0.42
     ফলে
    0.42
    アイテム
    0.42
    攷
    0.42
    ITest
    0.41
    ్ఞ
    0.41
    POST
    0.41
    POSITIVE LOGITS
     управ
    0.52
     बेहत
    0.44
     betterment
    0.43
    hern
    0.43
    ing
    0.42
     пользу
    0.42
     Louvre
    0.42
    赚钱
    0.42
     мра
    0.42
     bottomLeft
    0.41
    Act Density 0.000%

    No Known Activations