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

    Neuronpedia

    INDEX
    Explanations

    fidgeting in the game

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.62
     alebo
    0.61
     или
    0.58
     pero
    0.57
     oppure
    0.56
     ولكن
    0.55
    或者是
    0.54
    2
    0.54
     eller
    0.53
     czyli
    0.53
    POSITIVE LOGITS
    毕竟
    0.61
     sürekli
    0.53
     అవకాశం
    0.52
    这么多
    0.52
    indeki
    0.51
    那么多
    0.51
    缺乏
    0.51
    គ្មាន
    0.51
     ઘણા
    0.49
     Unlike
    0.49
    Act Density 0.009%

    No Known Activations