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

    Neuronpedia

    INDEX
    Explanations

    ความ followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কল্প
    0.44
    妑
    0.44
    सामान्यीकृत
    0.44
    굿
    0.42
     Circles
    0.42
    瑗
    0.41
     মুজিবর
    0.41
    사용
    0.40
     tiers
    0.39
    隰
    0.39
    POSITIVE LOGITS
    тельность
    0.42
    uda
    0.41
    bilisi
    0.39
    是非
    0.38
     lega
    0.37
     бли
    0.36
     उत्सुक
    0.36
    rivastava
    0.36
     permittivity
    0.36
    ikaze
    0.35
    Act Density 0.003%

    No Known Activations