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

    Neuronpedia

    INDEX
    Explanations

    non-English words or scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NEET
    0.45
     Electromagnetic
    0.44
     water
    0.44
     Cycling
    0.43
     inlet
    0.43
    inh
    0.42
     নিন
    0.42
     wheeled
    0.41
    রাই
    0.39
    ínio
    0.39
    POSITIVE LOGITS
     शिवसेना
    0.49
    Пер
    0.45
    。《
    0.45
    フォー
    0.45
    感謝
    0.45
     отзы
    0.45
     ቫ
    0.44
     كور
    0.44
    Мне
    0.44
     ассоциа
    0.43
    Act Density 0.003%

    No Known Activations