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

    Neuronpedia

    INDEX
    Explanations

    Intelligence, problem-solving, replicate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मुझे
    0.47
     of
    0.41
     ನನಗೆ
    0.39
     to
    0.39
     myself
    0.38
    给我
    0.37
     forem
    0.37
     меня
    0.36
     abusing
    0.36
     Of
    0.36
    POSITIVE LOGITS
    راث
    0.47
    चलिए
    0.44
    ากาศ
    0.44
    য়োজন
    0.44
     पैक
    0.43
     চলুন
    0.43
     धा
    0.42
    fontawesome
    0.42
     इच्छुक
    0.41
    पो
    0.41
    Act Density 0.002%

    No Known Activations