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

    Neuronpedia

    INDEX
    Explanations

    percentages, lists, etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    It
    0.42
    นั้น
    0.40
    Its
    0.40
    こちらの
    0.39
    比如说
    0.37
    They
    0.36
    들이
    0.35
    These
    0.34
     цьому
    0.34
    ה
    0.34
    POSITIVE LOGITS
    ﻥ
    0.39
    ১০
    0.35
    껑
    0.34
     goalkeeper
    0.33
    veel
    0.33
    ২৮
    0.32
     مدير
    0.32
     отсутствует
    0.32
     беремен
    0.32
     livré
    0.32
    Act Density 2.792%

    No Known Activations