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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    教育部
    0.39
    प
    0.37
    ាម
    0.37
    理
    0.36
     кеңсе
    0.36
     باول
    0.35
     hsize
    0.35
    ایہ
    0.35
     mè
    0.35
     elastomers
    0.35
    POSITIVE LOGITS
     અથવા
    0.50
     किंवा
    0.50
     или
    0.50
     veya
    0.49
     অথবা
    0.48
     ಅಥವಾ
    0.48
    之类的
    0.48
     slogan
    0.46
     hoặc
    0.46
    
    0.46
    Act Density 0.174%

    No Known Activations