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

    Neuronpedia

    INDEX
    Explanations

    breaking point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Awareness
    0.42
     homogen
    0.42
     Wealth
    0.39
    Wealth
    0.38
    Plate
    0.37
    CTOR
    0.37
    plate
    0.37
    PLATE
    0.37
    プレート
    0.37
     Plate
    0.36
    POSITIVE LOGITS
    ऍ
    0.38
    震惊
    0.38
    上帝
    0.38
     trás
    0.37
     اقوام
    0.36
     mimpi
    0.35
    灾
    0.35
     горе
    0.35
     chiến
    0.35
     приме
    0.35
    Act Density 0.001%

    No Known Activations