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

    Neuronpedia

    INDEX
    Explanations

    list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    但是
    0.46
    ppure
    0.44
    0.43
     Итак
    0.42
    ளிடையே
    0.40
    但是我
    0.38
     নাকি
    0.38
     但是
    0.37
    liquer
    0.37
    その他の
    0.37
    POSITIVE LOGITS
    ，
    0.93
    ،
    0.93
     ensuring
    0.91
     allowing
    0.88
     providing
    0.86
    ,
    0.80
     wobei
    0.79
     असून
    0.79
     있으며
    0.78
     podendo
    0.78
    Act Density 0.132%

    No Known Activations