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

    Neuronpedia

    INDEX
    Explanations

    assignment of values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feed
    0.38
     neutralize
    0.36
     squash
    0.36
    粒子
    0.35
     neutral
    0.35
     tempi
    0.35
    وض
    0.34
     balls
    0.34
     varsa
    0.34
     Feed
    0.34
    POSITIVE LOGITS
    omás
    0.44
     კომ
    0.43
     aisément
    0.43
    ⤟
    0.42
    でもある
    0.40
     २५
    0.39
     berusia
    0.38
     எட்டு
    0.38
    lungs
    0.38
    年
    0.38
    Act Density 0.017%

    No Known Activations