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

    Neuronpedia

    INDEX
    Explanations

    not significant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    最初は
    0.47
     그러나
    0.46
     nejen
    0.42
    !',
    0.41
     Einige
    0.41
    のではなく
    0.39
    어져
    0.39
    ইতে
    0.39
     있지만
    0.38
    그러나
    0.38
    POSITIVE LOGITS
     significant
    0.60
     significativa
    0.58
     appreciably
    0.57
    significant
    0.52
     meaningful
    0.51
     substantial
    0.51
     significative
    0.50
     major
    0.49
     значи
    0.49
    Significant
    0.48
    Act Density 0.230%

    No Known Activations