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

    Neuronpedia

    INDEX
    Explanations

    DOM elements, God or, drop or, odd numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    普及
    0.51
     выс
    0.49
    ній
    0.49
     موسی
    0.48
    нига
    0.46
     ακ
    0.45
     বিখ্যাত
    0.44
    ון
    0.43
     Picasso
    0.43
     учены
    0.43
    POSITIVE LOGITS
     sobre
    0.46
     الطريق
    0.46
    〒
    0.46
     وهي
    0.46
    ":
    0.45
    Animated
    0.45
     Szen
    0.45
    掙
    0.44
     secreto
    0.44
    sobre
    0.44
    Act Density 0.001%

    No Known Activations