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

    Neuronpedia

    INDEX
    Explanations

    first product

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deleteTask
    0.45
     tron
    0.45
     calomel
    0.44
     رعایت
    0.43
     Verwaltung
    0.43
     জীববিজ্ঞান
    0.43
     разговор
    0.43
     pregn
    0.42
     excitations
    0.42
     reduz
    0.42
    POSITIVE LOGITS
    Korea
    0.43
    M
    0.42
    【
    0.42
    Drop
    0.42
    推
    0.42
    한국
    0.41
    韓国
    0.40
    韩国
    0.40
    Maker
    0.40
    金
    0.39
    Act Density 0.000%

    No Known Activations