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

    Neuronpedia

    INDEX
    Explanations

    feeling or feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的工作
    1.57
    krieg
    1.55
    wolves
    1.49
     таки
    1.45
     Dysfunction
    1.44
    ى
    1.43
     ทำ
    1.41
    乎
    1.41
     chương
    1.33
     tướng
    1.30
    POSITIVE LOGITS
    ส์
    1.84
    де
    1.83
    دام
    1.81
    م
    1.80
    おそらく
    1.74
    ب
    1.73
    ز
    1.70
    వ
    1.61
    აც
    1.56
    t
    1.56
    Act Density 0.019%

    No Known Activations