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

    Neuronpedia

    INDEX
    Explanations

    identifiers followed by underscore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SharePoint
    0.81
     auspices
    0.76
     plural
    0.74
     Preface
    0.73
     ADHD
    0.71
     Hadoop
    0.69
     ArcGIS
    0.69
     IntelliJ
    0.68
     Revit
    0.68
     Kubernetes
    0.67
    POSITIVE LOGITS
    _
    2.92
    \_
    1.78
    __
    1.47
    _[
    1.47
    _*
    1.37
    _{
    1.32
    _%
    1.26
    _(
    1.25
    _'
    1.21
    _\
    1.18
    Act Density 0.775%

    No Known Activations