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

    Neuronpedia

    INDEX
    Explanations

    standard, single, Piece

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spam
    0.41
    的核心
    0.40
     persuasion
    0.38
     userdata
    0.38
     sincerity
    0.38
     Sausage
    0.37
    རྒྱ
    0.37
     wigs
    0.36
     deleniti
    0.36
    蚌
    0.36
    POSITIVE LOGITS
     সেনাবাহিনীকে
    0.38
     फ्र
    0.37
     Prest
    0.36
     quadrato
    0.36
     Prepar
    0.35
     Quem
    0.34
    แก้
    0.34
    俱乐
    0.34
    مار
    0.33
     Veter
    0.33
    Act Density 0.007%

    No Known Activations