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

    Neuronpedia

    INDEX
    Explanations

    verify and print

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wit
    0.40
    etary
    0.38
    Якщо
    0.37
    Issues
    0.37
    Wit
    0.37
    Blank
    0.36
     අන
    0.36
    et
    0.35
    arup
    0.35
    Limitations
    0.35
    POSITIVE LOGITS
     проверить
    0.46
    看看
    0.46
     mostrando
    0.46
     evolución
    0.43
    を確認
    0.43
     verifica
    0.43
     muestran
    0.42
    변경된
    0.42
     Afterward
    0.42
     afterwards
    0.42
    Act Density 0.111%

    No Known Activations