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

    Neuronpedia

    INDEX
    Explanations

    explaining how numbers or costs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enforces
    0.42
     examines
    0.40
     materialistic
    0.40
     covalently
    0.39
     Wissenschaft
    0.38
     stets
    0.37
     softwares
    0.37
     durchaus
    0.37
     Seiten
    0.37
     Baillargeon
    0.37
    POSITIVE LOGITS
     eZ
    0.43
    calendar
    0.42
     historiques
    0.42
    𝕊
    0.40
     históricos
    0.40
    හ
    0.39
     распро
    0.39
    ГЭ
    0.39
     lihtsalt
    0.38
     просто
    0.38
    Act Density 0.003%

    No Known Activations