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

    Neuronpedia

    INDEX
    Explanations

    types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ̀u
    0.46
     पांच
    0.46
     следующих
    0.45
     tujuh
    0.44
     تغییر
    0.43
     удобно
    0.43
    nutrition
    0.42
     acclaimed
    0.41
    နှစ်
    0.41
     पाच
    0.41
    POSITIVE LOGITS
     types
    0.90
    Types
    0.73
    types
    0.71
    类型的
    0.65
     Types
    0.63
     tipos
    0.61
     أنواع
    0.61
     kelamin
    0.58
     TYPES
    0.58
     soorten
    0.57
    Act Density 0.113%

    No Known Activations