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

    Neuronpedia

    INDEX
    Explanations

    Specifically, choices, concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     objections
    0.49
     行政
    0.46
     arrogant
    0.46
    lanelet
    0.46
     Wasserstein
    0.46
     discretionary
    0.46
     Ники
    0.44
    ặng
    0.44
     FLAGS
    0.44
     wildfires
    0.44
    POSITIVE LOGITS
    명
    0.47
    약
    0.46
    ล่าสุด
    0.45
    ศัพท์
    0.44
    의
    0.44
    보
    0.44
    nya
    0.43
    żyt
    0.43
    กว่า
    0.43
    בור
    0.42
    Act Density 0.003%

    No Known Activations