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

    Neuronpedia

    INDEX
    Explanations

    M1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tumult
    0.39
     considera
    0.38
     وان
    0.37
     تق
    0.37
     مقاب
    0.35
     Kolmogorov
    0.35
     monograph
    0.35
     pontos
    0.34
     tractable
    0.34
     Decre
    0.34
    POSITIVE LOGITS
    ק
    0.46
     businesses
    0.35
    餐厅
    0.35
    업
    0.35
    销售
    0.35
     athletes
    0.34
    я
    0.34
     sports
    0.34
    이트
    0.34
    ικού
    0.34
    Act Density 0.310%

    No Known Activations