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

    Neuronpedia

    INDEX
    Explanations

    combining things with others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    就算
    0.66
     Emeritus
    0.63
     Nich
    0.59
    0
    0.57
    的数据
    0.54
     Viceroy
    0.54
     reptiles
    0.54
    og
    0.52
    的部分
    0.52
     Vergleich
    0.52
    POSITIVE LOGITS
    在一起
    0.73
     સાથે
    0.73
     therewith
    0.71
    র
    0.71
    กับ
    0.70
     seamlessly
    0.66
     lângă
    0.65
     intégr
    0.65
     ajout
    0.64
     với
    0.64
    Act Density 0.024%

    No Known Activations