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

    Neuronpedia

    INDEX
    Explanations

    programming code and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ႄ
    0.46
     necessarily
    0.41
    ให้บริการ
    0.39
     maintained
    0.39
    必然
    0.38
     winery
    0.38
    ounter
    0.38
     washer
    0.37
    जरीवाल
    0.37
     operative
    0.37
    POSITIVE LOGITS
    捙
    0.44
    䀘
    0.42
    abı
    0.42
    葲
    0.42
    ভিউ
    0.41
    arzt
    0.41
    ikale
    0.41
    捚
    0.41
    studentid
    0.41
    哴
    0.40
    Act Density 0.004%

    No Known Activations