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

    Neuronpedia

    INDEX
    Explanations

    conditions involving if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    *.
    0.36
     ধ
    0.35
    ようです
    0.34
     estás
    0.33
    Ᏹ
    0.33
    ittarius
    0.33
     pake
    0.32
     máte
    0.32
     duit
    0.32
     september
    0.32
    POSITIVE LOGITS
     если
    1.16
     if
    1.11
     nếu
    1.09
     якщо
    1.09
     اگر
    1.06
     إذا
    1.06
     अगर
    1.04
     hvis
    1.04
    если
    1.03
     jika
    1.02
    Act Density 0.308%

    No Known Activations