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

    Neuronpedia

    INDEX
    Explanations

    ingredients or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이
    0.45
    history
    0.44
    eliz
    0.44
    Sunrise
    0.44
    promises
    0.43
    heres
    0.43
    defi
    0.43
    sunrise
    0.42
    >';
    0.42
    ्ले
    0.41
    POSITIVE LOGITS
     örg
    0.44
     Gérard
    0.41
     \]
    0.39
     détail
    0.38
     গম
    0.38
    钢
    0.38
    াক্ষ
    0.38
     зазна
    0.38
     Oleg
    0.38
     seleção
    0.38
    Act Density 0.001%

    No Known Activations