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

    Neuronpedia

    INDEX
    Explanations

    categorized for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Applicable
    0.81
    对
    0.76
     Aussch
    0.75
     כאשר
    0.72
     acry
    0.71
     applicable
    0.70
     Applies
    0.70
    相对于
    0.70
     Applied
    0.69
    對
    0.68
    POSITIVE LOGITS
    进行了
    1.02
    សម្រាប់ការ
    1.01
     进行
    0.99
     undergoing
    0.97
    进行
    0.93
     للت
    0.93
     underwent
    0.91
    สำหรับการ
    0.89
     undergoes
    0.88
     for
    0.87
    Act Density 0.474%

    No Known Activations