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

    Neuronpedia

    INDEX
    Explanations

    information and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.51
    ્સ
    0.48
     batas
    0.47
    がん
    0.46
    goers
    0.45
    ﺃ
    0.45
    ನಲ್ಲಿ
    0.45
     U
    0.44
     goal
    0.44
    E
    0.44
    POSITIVE LOGITS
     информацию
    0.61
     अबाउट
    0.54
     информация
    0.54
     расположен
    0.48
     статистика
    0.46
     Broch
    0.46
     informace
    0.45
     údaje
    0.45
    alista
    0.43
    ർ
    0.43
    Act Density 1.788%

    No Known Activations