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

    Neuronpedia

    INDEX
    Explanations

    qualifier noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aspects
    0.46
     basics
    0.45
     Aspects
    0.42
     aspectos
    0.40
     trends
    0.39
     Basics
    0.39
    Fundamentals
    0.39
     aspek
    0.38
     decisions
    0.38
     aspekt
    0.36
    POSITIVE LOGITS
    kish
    0.40
     albeit
    0.39
    नांक
    0.38
     posthum
    0.38
     typographical
    0.37
    <unused2126>
    0.37
    нную
    0.37
    ͆
    0.35
    emar
    0.35
    beatable
    0.34
    Act Density 0.025%

    No Known Activations