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

    Neuronpedia

    INDEX
    Explanations

    specific entities in requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     five
    1.11
     fifteen
    1.07
    。...
    1.01
     three
    0.99
     thor
    0.98
     twenty
    0.97
     thirty
    0.94
     chern
    0.91
     convin
    0.91
     ovaj
    0.91
    POSITIVE LOGITS
     বা
    0.85
    Capabilities
    0.85
    等的
    0.82
    ங்களில்
    0.82
    ለመ
    0.81
    명이
    0.80
     관련
    0.79
     ресурсов
    0.79
     फं
    0.78
    Component
    0.78
    Act Density 0.413%

    No Known Activations