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

    Neuronpedia

    INDEX
    Explanations

    easiest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     カスタ
    0.45
     Etc
    0.45
     पीपल
    0.45
    র
    0.45
    nosť
    0.44
     svých
    0.43
     Decision
    0.43
     Вікі
    0.43
     los
    0.42
     нови
    0.42
    POSITIVE LOGITS
    Benchmarks
    0.46
     benchmarking
    0.44
    там
    0.43
     وہاں
    0.42
    sud
    0.42
    να
    0.41
    ابل
    0.40
    Ratings
    0.40
    ratings
    0.40
     نیچے
    0.39
    Act Density 0.002%

    No Known Activations