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

    Neuronpedia

    INDEX
    Explanations

    . followed punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.95
     throughout
    0.93
     khắp
    0.90
     ఉంటాయి
    0.89
     rarely
    0.86
    стные
    0.86
     everywhere
    0.86
     luôn
    0.85
    .
    0.84
     πάντα
    0.84
    POSITIVE LOGITS
    িয়াছিল
    1.09
    لة
    0.91
    وقال
    0.90
    改成
    0.89
    ಾಯಿತು
    0.87
     ولی
    0.85
    队员
    0.85
     %>',
    0.84
    ছিল
    0.81
     aggiungere
    0.80
    Act Density 0.039%

    No Known Activations