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

    Neuronpedia

    INDEX
    Explanations

    just one part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ంచరీలు
    0.84
     основных
    0.83
     directe
    0.80
    故意
    0.79
     básica
    0.79
    ्युअर
    0.78
    ıyla
    0.78
    ों
    0.77
     estándar
    0.77
     standart
    0.76
    POSITIVE LOGITS
     part
    1.20
    part
    0.97
     جزء
    0.97
     часть
    0.89
    PART
    0.85
    一部分
    0.85
     parte
    0.85
    Part
    0.81
     بخشی
    0.78
     অংশ
    0.78
    Act Density 0.026%

    No Known Activations