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

    Neuronpedia

    INDEX
    Explanations

    structure followed by data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     അതിനാ
    0.32
    vény
    0.31
    ണ്ഡ
    0.30
     jako
    0.29
    ⎠
    0.28
    penas
    0.28
     krótk
    0.28
    nutí
    0.27
    Gert
    0.27
     संवेदना
    0.27
    POSITIVE LOGITS
    如下
    0.43
     {
    0.43
    0.39
    {
    0.37
            
    0.37
    ↵
    0.37
    以下の
    0.36
     다음과
    0.35
     följande
    0.34
    ：
    0.33
    Act Density 0.341%

    No Known Activations