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

    Neuronpedia

    INDEX
    Explanations

    database tables and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     numerador
    0.49
     sweaty
    0.43
    राबरी
    0.43
    硞
    0.43
     مثال
    0.42
     LongNumber
    0.41
     exothermic
    0.41
     baggy
    0.41
     உயிர்
    0.41
    akah
    0.40
    POSITIVE LOGITS
     Groups
    0.68
     groups
    0.66
     categories
    0.66
     species
    0.66
    Groups
    0.65
     brands
    0.65
     types
    0.63
     Species
    0.63
     Categories
    0.62
     users
    0.61
    Act Density 0.045%

    No Known Activations