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

    Neuronpedia

    INDEX
    Explanations

    providing explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سنی
    0.54
    être
    0.49
    isel
    0.49
     outlier
    0.49
     किमी
    0.49
    frigerator
    0.47
     மய
    0.47
     идти
    0.46
    氓
    0.46
    inz
    0.46
    POSITIVE LOGITS
    ки
    0.45
     prepar
    0.42
     manifeste
    0.42
     prepares
    0.41
     schema
    0.39
     koost
    0.39
     sor
    0.39
     manifi
    0.39
    es
    0.38
    c
    0.38
    Act Density 0.001%

    No Known Activations