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

    Neuronpedia

    INDEX
    Explanations

    temporal conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused558>
    0.48
    iejęt
    0.46
     bedeutet
    0.46
    Issledovatel
    0.46
     besucht
    0.45
    җ
    0.45
    ählten
    0.45
     spielen
    0.45
     revêtu
    0.45
    <unused470>
    0.44
    POSITIVE LOGITS
     unsustainable
    0.45
     Unfortunately
    0.44
    0.43
    Unfortunately
    0.43
     unfortunately
    0.42
     Thankfully
    0.41
     realignment
    0.40
     மொத்தம்
    0.40
    開始
    0.40
    最終
    0.40
    Act Density 0.004%

    No Known Activations