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

    Neuronpedia

    INDEX
    Explanations

    comparisons using than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pero
    0.48
    但他
    0.46
     ብቻ
    0.46
     nejen
    0.45
     but
    0.44
     BUT
    0.42
    ATIONS
    0.40
     seulement
    0.40
    λλά
    0.40
    但
    0.40
    POSITIVE LOGITS
     than
    1.27
    than
    1.10
     decât
    1.10
     niż
    1.08
     kuin
    1.06
     чем
    0.99
     ніж
    0.92
    กว่า
    0.92
     daripada
    0.91
     než
    0.91
    Act Density 0.173%

    No Known Activations