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

    Neuronpedia

    INDEX
    Explanations

    numbers, quantities, or prices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     specific
    0.90
     Adobe
    0.73
     hel
    0.73
     Google
    0.70
     potent
    0.69
     sections
    0.69
     luc
    0.69
     section
    0.68
     ri
    0.67
     desktop
    0.67
    POSITIVE LOGITS
    ⦕
    1.15
    ⤠
    1.05
    INTEGER
    1.02
    ཥ
    1.01
    ikhil
    1.01
    Quantidade
    1.01
     wwwpond
    1.00
    Giá
    0.99
    Số
    0.99
    𐰤
    0.99
    Act Density 0.796%

    No Known Activations