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

    Neuronpedia

    INDEX
    Explanations

    structure closing brace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     opaque
    0.53
     പറയ
    0.47
    <unused266>
    0.46
     реаль
    0.46
     объекта
    0.45
     yüz
    0.45
     reshape
    0.45
     örne
    0.44
     misalnya
    0.43
     সম্পূর্ণ
    0.43
    POSITIVE LOGITS
    court
    0.48
    0
    0.45
     trocar
    0.44
    struck
    0.43
    der
    0.42
    躬
    0.42
    bolt
    0.42
    sponsored
    0.41
    marketplace
    0.40
    anor
    0.39
    Act Density 0.000%

    No Known Activations