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

    Neuronpedia

    INDEX
    Explanations

    everything is sewn together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    beginning
    0.40
    linetype
    0.39
    leftChild
    0.37
    某一
    0.37
    cloud
    0.36
    піль
    0.36
    薀
    0.36
     단순
    0.36
    criminals
    0.35
    obstacles
    0.35
    POSITIVE LOGITS
    ĵo
    0.48
     complementar
    0.43
     complementary
    0.42
     simult
    0.41
     similarly
    0.41
     Viator
    0.40
     ĝi
    0.40
     处理
    0.39
    oretum
    0.39
     tudo
    0.38
    Act Density 0.000%

    No Known Activations