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

    Neuronpedia

    INDEX
    Explanations

    storing information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لي
    0.49
    ادي
    0.47
    bringen
    0.42
    ٤
    0.41
    攞
    0.41
    ඖ
    0.41
    ان
    0.41
    ير
    0.40
    vé
    0.40
     ప్రభ
    0.40
    POSITIVE LOGITS
     저장
    1.09
     storage
    1.01
     storing
    0.96
     almacenamiento
    0.92
     ذخ
    0.91
     disimpan
    0.86
     保存
    0.86
     penyimpanan
    0.86
     хранения
    0.84
     menyimpan
    0.83
    Act Density 0.075%

    No Known Activations