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

    Neuronpedia

    INDEX
    Explanations

    final answer or total

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    constraintTop
    0.35
    מיד
    0.33
     proactively
    0.32
    िच
    0.31
     prvo
    0.31
    putar
    0.31
    ὤ
    0.31
     ویس
    0.30
    轆
    0.30
    sprecher
    0.30
    POSITIVE LOGITS
     final
    4.44
    final
    3.91
    最終
    3.72
     Final
    3.61
    Final
    3.61
     FINAL
    3.55
     최종
    3.50
    最终
    3.48
    FINAL
    3.34
     फाइनल
    3.28
    Act Density 0.234%

    No Known Activations