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

    Neuronpedia

    INDEX
    Explanations

    trash talk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مهم
    0.46
    ording
    0.41
     aksi
    0.39
    ကျ
    0.38
     σημαν
    0.38
     ചില
    0.38
     Attendance
    0.38
    重要的
    0.37
     حمایت
    0.37
     Numer
    0.37
    POSITIVE LOGITS
     aeropuerto
    0.51
     राउत
    0.48
     কাপড়
    0.46
     eloqu
    0.46
    atória
    0.46
     হেলিকপ্ট
    0.46
    యిత
    0.45
    er
    0.45
    భర
    0.45
     mimics
    0.44
    Act Density 0.001%

    No Known Activations