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

    Neuronpedia

    INDEX
    Explanations

    own abilities and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    এবং
    0.82
    重要な
    0.82
    Moreover
    0.79
     ersche
    0.77
     లక్ష
    0.76
    örungen
    0.76
    具有
    0.75
     अथवा
    0.75
    iremos
    0.75
     महत्त्वपूर्ण
    0.75
    POSITIVE LOGITS
     myself
    1.60
    我自己
    0.98
     Myself
    0.95
     tbh
    0.94
     saya
    0.91
     خودم
    0.88
    私は
    0.83
     نفسي
    0.81
    但我
    0.80
     আছি
    0.78
    Act Density 0.040%

    No Known Activations