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

    Neuronpedia

    INDEX
    Explanations

    description and help text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     frå
    0.39
     Prose
    0.39
     dets
    0.37
     Soup
    0.36
    τέ
    0.35
     Substance
    0.35
     ismi
    0.35
     সিনে
    0.35
     اسمها
    0.35
     trast
    0.34
    POSITIVE LOGITS
    This
    0.56
    description
    0.54
     Beschreibung
    0.54
    Description
    0.50
     Descripción
    0.49
    DESCRIPTION
    0.49
    Allows
    0.48
    Provides
    0.47
    説明
    0.47
     Describes
    0.47
    Act Density 0.090%

    No Known Activations