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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ק
    0.47
     yogurt
    0.46
     curd
    0.46
     shrimp
    0.45
     نہیں۔
    0.43
    dict
    0.42
    BOOL
    0.42
     copying
    0.42
     meringue
    0.41
     triggered
    0.41
    POSITIVE LOGITS
    anın
    0.47
    arów
    0.46
    ostęp
    0.45
     vän
    0.43
    igheder
    0.42
    ઓની
    0.42
     있다는
    0.41
    中的
    0.41
     записи
    0.41
    amot
    0.41
    Act Density 0.000%

    No Known Activations