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

    Neuronpedia

    INDEX
    Explanations

    compound concepts and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     လက်
    0.62
    <unused1071>
    0.57
     فقط
    0.55
    ները
    0.54
     მხოლოდ
    0.54
     DENUMIRE
    0.52
     толькі
    0.52
    ならば
    0.52
     ﺍﻟ
    0.52
     குவி
    0.52
    POSITIVE LOGITS
    is
    0.61
    ق
    0.57
      
    0.51
    isely
    0.46
    I
    0.46
    ствен
    0.46
     vog
    0.45
     a
    0.45
    er
    0.45
    ing
    0.45
    Act Density 0.001%

    No Known Activations