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

    Neuronpedia

    INDEX
    Explanations

    fundraising for support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺮ
    0.48
    ريكية
    0.47
    dagog
    0.44
    тего
    0.44
    Disha
    0.43
     Probleme
    0.43
    ۹
    0.43
     سوشل
    0.43
    બ
    0.43
    ід
    0.42
    POSITIVE LOGITS
     to
    0.51
     eventual
    0.49
     various
    0.48
     aquatic
    0.47
     anticipate
    0.46
    。</
    0.46
     expect
    0.46
     northward
    0.46
     future
    0.46
     await
    0.46
    Act Density 0.017%

    No Known Activations