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

    Neuronpedia

    INDEX
    Explanations

    pointingpayFromDuringfor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    谙
    0.33
    िसोदिया
    0.32
     hinsichtlich
    0.31
    декс
    0.30
     असतो
    0.30
    تباين
    0.30
    о
    0.30
    leşik
    0.29
     potencialmente
    0.29
     perplexing
    0.29
    POSITIVE LOGITS
     from
    0.54
     by
    0.53
     từ
    0.49
     during
    0.45
    จาก
    0.43
     for
    0.38
     donated
    0.38
     prédio
    0.37
     From
    0.37
     Từ
    0.36
    Act Density 0.000%

    No Known Activations