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

    Neuronpedia

    INDEX
    Explanations

    how things work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ለኛ
    0.41
    но
    0.39
    ба
    0.38
    ριο
    0.38
    노
    0.38
     পারেনি
    0.37
    のみ
    0.36
    仅
    0.36
    ুটি
    0.36
     chỉ
    0.35
    POSITIVE LOGITS
     actually
    0.51
    </h2>
    0.46
    ？
    0.46
    ؟
    0.44
    ということ
    0.44
    actually
    0.44
    ？！
    0.44
     (&
    0.43
     एक्चुअली
    0.42
     Actually
    0.42
    Act Density 0.043%

    No Known Activations