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

    Neuronpedia

    INDEX
    Explanations

    types, varieties, forms, subspecies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कारक
    0.40
    multiSelectList
    0.39
    राष्ट्र
    0.39
    inputSelect
    0.38
     দৃ
    0.38
     возвра
    0.37
    гну
    0.37
     =========
    0.37
    ']},
    0.36
     भोजन
    0.36
    POSITIVE LOGITS
     subtypes
    1.75
     varieties
    1.72
     subtype
    1.70
     разнови
    1.57
     variants
    1.54
     variant
    1.53
     Varieties
    1.53
     types
    1.52
     variedades
    1.52
     subspecies
    1.52
    Act Density 0.059%

    No Known Activations