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

    Neuronpedia

    INDEX
    Explanations

    variety of AI tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     settle
    0.45
     mekanisme
    0.43
     dene
    0.41
     population
    0.40
     investigating
    0.39
    人口
    0.39
     siap
    0.38
     finish
    0.38
     investigate
    0.38
     settles
    0.38
    POSITIVE LOGITS
    ZP
    0.46
     Memoir
    0.41
    ština
    0.41
     Transvaal
    0.40
    配置文件
    0.39
    μφωνα
    0.39
    стаў
    0.39
    tempHeader
    0.39
    തന്ത്ര
    0.38
    AuthProvider
    0.38
    Act Density 0.004%

    No Known Activations