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
    য়োজনীয়
    0.44
    ølge
    0.39
    ქვენ
    0.37
     chodzi
    0.37
    0.35
    νά
    0.35
     ആയ
    0.34
    ಿಸಲಾಗಿದೆ
    0.34
    ürnberg
    0.34
    چہ
    0.34
    POSITIVE LOGITS
     if
    3.75
     nếu
    3.58
     если
    3.56
     якщо
    3.39
     إذا
    3.28
     dacă
    3.28
     اگر
    3.23
     jika
    3.23
     jeśli
    3.14
     अगर
    3.09
    Act Density 0.285%

    No Known Activations