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

    Neuronpedia

    INDEX
    Explanations

    naming or terms used

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ائرة
    0.37
    注意事项
    0.36
     ಸಹ
    0.36
     ብቻ
    0.35
     ಒಬ್ಬ
    0.35
     පමණ
    0.34
    ':[
    0.34
    事业单位
    0.34
    ിയും
    0.33
    হাব
    0.33
    POSITIVE LOGITS
     called
    2.56
     termed
    2.33
    called
    2.28
    稱為
    2.27
     Called
    2.17
    称为
    2.17
     disebut
    2.16
     называется
    2.11
     называ
    2.08
     sogenannten
    2.06
    Act Density 0.137%

    No Known Activations