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

    Neuronpedia

    INDEX
    Explanations

    suspicious activity detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    टेगरी
    0.40
     idols
    0.40
    Visibility
    0.40
     Interessen
    0.40
     visibility
    0.39
     seize
    0.39
    願意
    0.38
    CategoryImage
    0.38
    visibility
    0.38
    ल्ली
    0.38
    POSITIVE LOGITS
     suspicious
    1.00
     activity
    0.87
    activity
    0.81
     Activity
    0.79
     suspiciously
    0.77
     actividad
    0.76
    Activity
    0.73
     unusual
    0.73
     활동
    0.73
     गतिविधि
    0.72
    Act Density 0.004%

    No Known Activations