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

    Neuronpedia

    INDEX
    Explanations

    focused on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    에
    1.19
    的不
    1.15
    まして
    1.10
     meisten
    1.01
    이면
    1.00
    年的
    1.00
     questione
    1.00
     lleva
    0.98
     וכ
    0.98
     nevoie
    0.98
    POSITIVE LOGITS
    oak
    1.21
    m
    1.15
    ocean
    1.06
    t
    1.05
    ابية
    1.03
    toys
    1.02
    idious
    1.01
    time
    1.00
    য়াস
    1.00
    tolist
    1.00
    Act Density 0.261%

    No Known Activations