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

    Neuronpedia

    INDEX
    Explanations

    attributes, fields, or properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     attribute
    0.47
     Attribute
    0.47
    బి
    0.46
    ენა
    0.45
     parámetro
    0.44
    Stored
    0.44
     Attributes
    0.43
    属性
    0.43
     attributes
    0.43
     Variables
    0.42
    POSITIVE LOGITS
    Ụ
    0.41
    centage
    0.40
    speedboat
    0.40
    დაც
    0.39
    set
    0.38
    whose
    0.38
     invitations
    0.37
    名叫
    0.37
     budgets
    0.37
     gac
    0.37
    Act Density 0.047%

    No Known Activations