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

    Neuronpedia

    INDEX
    Explanations

    AI stress testing and monitoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Caption
    0.49
    caption
    0.43
    [*
    0.40
    Компания
    0.40
     Caption
    0.40
    Dubai
    0.39
    ሺ
    0.39
     captions
    0.39
     شوی
    0.39
    МО
    0.38
    POSITIVE LOGITS
     Unity
    0.39
     unchallenged
    0.39
     Glucose
    0.38
     hills
    0.38
     ’
    0.38
     ».
    0.38
    了承
    0.38
     UnityEngine
    0.37
    ceries
    0.37
     Offline
    0.37
    Act Density 0.000%

    No Known Activations