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

    Neuronpedia

    INDEX
    Explanations

    item, items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fuerzas
    0.78
     theories
    0.77
     sons
    0.76
     Theories
    0.76
    hna
    0.76
     ပြော
    0.74
     teorías
    0.71
    र्जी
    0.69
     بیٹے
    0.69
     말이
    0.67
    POSITIVE LOGITS
     item
    5.58
     Item
    5.39
    item
    5.25
     items
    5.14
     Items
    5.14
    Item
    5.11
    items
    5.00
     ITEM
    4.87
    Items
    4.81
    ITEM
    4.79
    Act Density 0.478%

    No Known Activations