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

    Neuronpedia

    INDEX
    Explanations

    поиск или попытка

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     succinct
    0.38
    ନ
    0.36
    ରା
    0.36
     succinctly
    0.34
     ạ
    0.33
    ல்
    0.32
    ଅ
    0.32
    ﭔ
    0.32
     measles
    0.32
     ánimo
    0.32
    POSITIVE LOGITS
    ри
    0.33
    oretically
    0.32
     якщо
    0.31
     jei
    0.31
    sächlich
    0.30
    ından
    0.30
     niektórych
    0.30
    помним
    0.29
     Шо
    0.29
    内容は
    0.29
    Act Density 0.004%

    No Known Activations