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

    Neuronpedia

    INDEX
    Explanations

    times, durations, and amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ോ
    0.41
     realtime
    0.38
    сро
    0.38
     réalisés
    0.37
    驛
    0.37
    實現
    0.36
     реализова
    0.36
     vyn
    0.36
    の実
    0.35
    串口
    0.35
    POSITIVE LOGITS
     abbastanza
    0.40
    ジェ
    0.39
     chuckled
    0.39
    க்கமாக
    0.39
     laugh
    0.38
    incer
    0.38
    怙
    0.36
     করেছিলাম
    0.36
    Before
    0.36
    \|_{\
    0.36
    Act Density 0.001%

    No Known Activations