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

    Neuronpedia

    INDEX
    Explanations

    life insurance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нора
    0.39
    中国的
    0.39
    behör
    0.38
     জটিল
    0.38
    的发展
    0.37
    了吗
    0.37
     hinted
    0.37
     memberships
    0.36
    $/../../../../
    0.36
    otum
    0.36
    POSITIVE LOGITS
     Phan
    0.42
     Dashboard
    0.38
    ୮
    0.36
     i
    0.36
     dashboard
    0.35
     звер
    0.35
     મા
    0.34
     пане
    0.34
     disebut
    0.34
    फान
    0.33
    Act Density 0.005%

    No Known Activations