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

    Neuronpedia

    INDEX
    Explanations

    dialogue history, driving time, safe space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ية
    0.45
     utilisent
    0.44
     وي
    0.44
     lend
    0.43
     وإ
    0.41
     تنس
    0.41
     قوس
    0.41
    ण्ट
    0.40
    拴
    0.40
     своему
    0.40
    POSITIVE LOGITS
     শাহ
    0.43
    Finish
    0.40
    ண்ட
    0.40
    Política
    0.39
     preceded
    0.39
     чтобы
    0.39
    Thai
    0.38
     Shah
    0.38
     more
    0.38
     State
    0.38
    Act Density 0.005%

    No Known Activations