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

    Neuronpedia

    INDEX
    Explanations

    AI, Google, AR, Type, Object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मस्
    0.64
     якщо
    0.61
     કહ
    0.58
     ป
    0.56
     મુદ્
    0.54
     বৈদেশিক
    0.53
     عشان
    0.52
     まず
    0.52
    ។
    0.52
    ː
    0.51
    POSITIVE LOGITS
     மட்டுமல்ல
    0.57
     अत्यधिक
    0.54
     harnessed
    0.51
    在我们
    0.50
     garb
    0.49
    ît
    0.49
     ankaŭ
    0.49
     staples
    0.49
    matically
    0.48
    గానే
    0.48
    Act Density 0.002%

    No Known Activations