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

    Neuronpedia

    INDEX
    Explanations

    Chinese threat, colony, reporting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     조성
    1.19
    실
    1.14
    زاده
    1.12
     উপদে
    1.12
     definitely
    1.12
     رح
    1.11
     이
    1.11
    ＆
    1.03
     certainly
    1.02
     Brü
    1.00
    POSITIVE LOGITS
     ठिकाणी
    1.04
     অন্তঃ
    0.91
     Tomlinson
    0.89
     raro
    0.86
     colonia
    0.85
     intelligible
    0.83
    [](
    0.82
     між
    0.82
    तरी
    0.82
    '\
    0.82
    Act Density 0.000%

    No Known Activations