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

    Neuronpedia

    INDEX
    Explanations

    specific topics or goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    फान
    0.49
    at
    0.47
     breakthrough
    0.44
    的价格
    0.44
     বিকল্প
    0.43
     mäng
    0.43
     réduire
    0.42
    瑞士
    0.42
    bal
    0.42
     halluc
    0.41
    POSITIVE LOGITS
     \
    0.54
     общения
    0.52
    ంబేద్కర్
    0.50
    чества
    0.50
    ج
    0.50
     UserService
    0.48
    ত
    0.48
    فى
    0.47
    Би
    0.47
     öyle
    0.46
    Act Density 0.001%

    No Known Activations