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

    Neuronpedia

    INDEX
    Explanations

    information given

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    开源
    0.55
    诸多
    0.52
     архіви
    0.52
    媟
    0.52
     можуть
    0.51
    窅
    0.51
    微软
    0.50
    하거나
    0.50
    相关
    0.50
    业界
    0.50
    POSITIVE LOGITS
     presumably
    0.62
     given
    0.56
     two
    0.55
     TWO
    0.53
     stated
    0.52
     diberikan
    0.51
     tenemos
    0.51
     $
    0.50
     robbers
    0.50
     $=
    0.50
    Act Density 0.291%

    No Known Activations