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

    Neuronpedia

    INDEX
    Explanations

    breakdown of explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sync
    0.52
    Lect
    0.47
     vý
    0.47
    Dump
    0.46
    ައ
    0.46
     zároveň
    0.46
    Minimize
    0.46
    Month
    0.45
    带
    0.45
    Lib
    0.44
    POSITIVE LOGITS
    attie
    0.45
    otted
    0.44
     E
    0.43
     bioactive
    0.42
    etica
    0.41
    inei
    0.41
    πον
    0.39
     सटीक
    0.39
     MRP
    0.39
    тики
    0.38
    Act Density 0.001%

    No Known Activations