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

    Neuronpedia

    INDEX
    Explanations

    final output processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    假设
    0.42
    oj
    0.38
     usadas
    0.37
    weapp
    0.37
     essentielles
    0.36
     жүктөө
    0.35
     ভেতরে
    0.35
     verändert
    0.35
    审核
    0.34
    进来
    0.34
    POSITIVE LOGITS
     final
    1.09
     최종
    1.02
    Final
    0.96
    最终
    0.96
    final
    0.94
     output
    0.93
    最終
    0.90
     оконча
    0.88
     Final
    0.87
    FINAL
    0.87
    Act Density 0.064%

    No Known Activations