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

    Neuronpedia

    INDEX
    Explanations

    more X than Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     für
    0.47
     nearer
    0.43
     untuk
    0.41
     conversely
    0.41
     deciduous
    0.41
    </h2>
    0.39
     wine
    0.39
     """
    0.39
     について
    0.39
     closer
    0.38
    POSITIVE LOGITS
    超过
    0.44
    がたくさん
    0.42
     exceeds
    0.42
    高于
    0.40
     dépass
    0.40
     détaillé
    0.39
     trống
    0.39
    ולד
    0.38
    룺
    0.38
     превы
    0.38
    Act Density 0.117%

    No Known Activations