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

    Neuronpedia

    INDEX
    Explanations

    if condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    まい
    0.35
     depende
    0.35
    ຕົ
    0.34
    Initialize
    0.34
     emphasized
    0.34
    typical
    0.34
     entendeu
    0.34
    depends
    0.33
    ことが多い
    0.33
    scopic
    0.33
    POSITIVE LOGITS
     nếu
    0.93
     если
    0.91
     if
    0.90
     jika
    0.88
     hvis
    0.87
     यदि
    0.85
    如果你
    0.85
     jeśli
    0.83
     إذا
    0.82
     চাইলে
    0.81
    Act Density 0.112%

    No Known Activations