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

    Neuronpedia

    INDEX
    Explanations

    Judeo-Christian understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дав
    0.46
    ധാ
    0.46
    例
    0.45
    ান্ট
    0.45
    сун
    0.43
    ПК
    0.43
    一群
    0.42
    ビネット
    0.41
    რავ
    0.41
    childComplexity
    0.41
    POSITIVE LOGITS
     tiens
    0.43
    𝗵
    0.43
     smelt
    0.42
     nieruchomości
    0.42
    to
    0.42
     sider
    0.41
     naše
    0.41
     dete
    0.41
    𝗼
    0.41
    booking
    0.40
    Act Density 0.006%

    No Known Activations