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

    Neuronpedia

    INDEX
    Explanations

    conditional statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wszystkie
    0.46
     all
    0.43
     műkö
    0.40
     kaikki
    0.40
     lahat
    0.39
    liği
    0.38
     donc
    0.36
     wszystkich
    0.36
     stets
    0.35
     zaten
    0.35
    POSITIVE LOGITS
     nếu
    1.34
     if
    1.32
     если
    1.30
     якщо
    1.28
     यदि
    1.23
     अगर
    1.20
     اگر
    1.17
     যদি
    1.16
     jika
    1.13
    если
    1.13
    Act Density 1.099%

    No Known Activations