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

    Neuronpedia

    INDEX
    Explanations

    if clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mungkin
    1.07
     whenever
    1.03
     may
    0.99
     optional
    0.98
     возмо
    0.96
    maybe
    0.94
     possibly
    0.94
    อาจ
    0.94
    possibly
    0.94
    可能
    0.91
    POSITIVE LOGITS
    çons
    0.87
    ផលិត
    0.83
    wyd
    0.78
    وریت
    0.76
    şiktaş
    0.76
    提出了
    0.75
    桡
    0.75
    घाडी
    0.75
    이드
    0.74
    럇
    0.74
    Act Density 0.113%

    No Known Activations