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

    Neuronpedia

    INDEX
    Explanations

    pairs of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    與
    0.48
     मिश्रण
    0.48
     प्रतिसाद
    0.47
     मद्देनजर
    0.46
     与
    0.45
     與
    0.45
     ඔවුන්
    0.45
    whitelist
    0.45
     நுழை
    0.44
    स्त्र
    0.44
    POSITIVE LOGITS
     intersecting
    0.45
     competing
    0.45
    ниці
    0.44
     opposing
    0.42
     interacting
    0.41
     halves
    0.41
    相邻
    0.41
     সমান
    0.40
     unequal
    0.40
     inequalities
    0.40
    Act Density 0.054%

    No Known Activations