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

    Neuronpedia

    INDEX
    Explanations

    the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ımızı
    0.46
    的存在
    0.43
    igheter
    0.39
    これを
    0.39
    などを
    0.38
     หลาย
    0.37
    ﺸ
    0.36
    及其
    0.35
    ówki
    0.35
     তারই
    0.35
    POSITIVE LOGITS
     the
    1.13
    the
    0.95
    The
    0.94
     The
    0.86
    該
    0.84
    nThe
    0.72
    该
    0.72
     该
    0.71
     ያለው
    0.69
    当該
    0.68
    Act Density 0.123%

    No Known Activations